Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@EDGAR Alert MCP Server Show me recent insider trades for Microsoft"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Connect Claude Desktop (or any MCP-compatible client) directly to your EDGAR Alert account. Ask live questions about SEC insider trading signals, Form 4 activity, 8-K officer/director changes, and company research context — without leaving your conversation.
Works on any paid EDGAR Alert plan. Most tools (latest alerts, search, company profiles, fundamentals, price windows) work on STARTER and PRO. One tool —
edgaralert_get_company_agent_context, the bundled AI research-context payload — requires Enterprise; on a lower plan it returns a clear upgrade message instead of failing silently. See Tools below for the full breakdown, and edgaralert.com/pricing to upgrade.
A thin, read-only wrapper around the existing public
https://api.edgaralert.com/api/v1 REST API. Every tool maps to exactly
one v1 endpoint.
No direct database access. No scoring or signal logic is duplicated here — all of that lives in the API, same as it does for every other v1 API consumer.
No write actions, no billing, no account management. This server cannot place orders, change your subscription, or modify settings of any kind.
Your API key is yours — you provide it, it is sent only to
api.edgaralert.com as the X-API-Key header, and this server never
writes it to disk or logs it.
Related MCP server: sec-edgar-mcp
Node.js 18.17 or later
An EDGAR Alert API key on any paid plan (get one here) — STARTER and PRO both work for most tools; Enterprise unlocks all 8.
.mcpb (recommended for most users)Download edgaralert-mcp.mcpb from the
latest release.
Open Claude Desktop → Settings → Extensions → Advanced settings → Install Extension, and select the downloaded file (or just drag the file onto the Claude Desktop window).
When prompted, paste your EDGAR Alert API key. Claude Desktop stores it securely in your OS keychain — this project never sees or stores it outside that prompt.
Restart Claude Desktop if prompted.
claude_desktop_config.jsonClone or download this folder (mcp-server/) somewhere on your machine.
Install dependencies and build:
cd mcp-server
npm install
npm run buildOpen your Claude Desktop config file:
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
Add an entry under mcpServers (see example below).
Restart Claude Desktop.
cd mcp-server
npm install
EDGARALERT_API_KEY=EA_your_key_here npm run devThis runs the server on stdio using tsx, without a build step. Useful
when iterating on tool definitions.
{
"mcpServers": {
"edgaralert": {
"command": "node",
"args": ["/absolute/path/to/mcp-server/dist/index.js"],
"env": {
"EDGARALERT_API_KEY": "EA_your_key_here"
}
}
}
}Replace /absolute/path/to/mcp-server/dist/index.js with the real path on
your machine, and EA_your_key_here with your actual EDGAR Alert API key.
Never commit this file with a real key in it.
Variable | Required | Default | Description |
| Yes | — | Your EDGAR Alert v1 API key. Sent as |
| No |
| Override for staging/local development. Most users should not set this. |
All tools are read-only. See docs/tools.md for full
input schemas, endpoint mappings, and error behavior.
Tool | Endpoint | Min. plan |
|
| STARTER |
|
| PRO |
|
| PRO |
|
| PRO |
|
| All paid |
|
| PRO |
|
| ENTERPRISE |
|
| None |
"Min. plan" reflects what the underlying API enforces today — STARTER
and PRO keys can use 7 of 8 tools. Only edgaralert_get_company_agent_context
requires Enterprise; on a lower-tier key it returns a clean 403 with an
upgrade message (see below) rather than failing silently or crashing.
"Your EDGAR Alert API key was rejected" — check EDGARALERT_API_KEY
is set and correct.
"This action requires a higher EDGAR Alert plan" — expected on
edgaralert_get_company_agent_context for STARTER/PRO keys; every
other tool should work normally on those plans. If you see this on a
different tool, double check your plan tier in the EDGAR Alert
dashboard.
"rate or daily quota exceeded" — you've hit your plan's API limits. Wait, or check usage in your EDGAR Alert dashboard.
"Could not reach the EDGAR Alert API" — a network/connectivity issue,
not an account issue. Run
node -e "fetch('https://api.edgaralert.com/api/v1/alerts/latest').then(r=>r.text()).then(console.log)"
— you should see a JSON error like {"message":"Missing X-API-Key header."} (that's expected and means the API is reachable). If you get
a DNS error (ENOTFOUND/ENODATA) or no response, the problem is
local network/DNS, not this server or your account.
"Unexpected token '<', is not valid JSON" — the request reached a
server, but got back an HTML page instead of API data. This happens if
EDGARALERT_BASE_URL is ever pointed at edgaralert.com or
www.edgaralert.com instead of api.edgaralert.com — the bare and
www hosts serve the marketing website (an Azure Static Web App), not
the API. The default in this package is already set to
api.edgaralert.com; if you see this error, check whether
EDGARALERT_BASE_URL has been overridden somewhere in your config.
This server has no admin, billing, or order-management capability of any kind — those endpoints are not implemented here, by design.
No secrets are hardcoded anywhere in this package. The only credential used is the one you supply via environment variable / Claude Desktop config.
No data is cached or persisted to disk between tool calls.
Network access is limited to EDGARALERT_BASE_URL (defaults to
api.edgaralert.com) — no other outbound calls are made.
npm run typecheck # type-check without emitting
npm run build # compile to dist/
npm run dev # run with tsx, no build stepTo add a new tool: copy the pattern in src/tools/getWeeklyInsights.ts (for
a no-input tool) or src/tools/searchAlerts.ts (for a filtered tool),
register it in src/tools/index.ts, and only ever call api/v1/* or other
already-public endpoints. Do not add database clients, Stripe/order
clients, or any write-capable tool to this package.
Adds a stock ticker to one of the user's ticker lists (watchlists). Use edgaralert_get_ticker_lists first to find the correct listId. Plan limits apply: FREE/STARTER plans are capped at 10 tickers total across all lists. Returns the created ticker list item on success.
| Name | Required | Description | Default |
|---|---|---|---|
| listId | Yes | The ID of the ticker list to add to. Get list IDs from edgaralert_get_ticker_lists. | |
| ticker | Yes | Stock ticker to add, e.g. AAPL. Will be uppercased automatically. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Discloses plan limits (FREE/STARTER capped at 10 tickers) and return value (created item). Annotations already indicate write operation (readOnlyHint=false) and non-destructive (destructiveHint=false), so description adds useful context without contradiction.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two succinct sentences that front-load the main action and include essential usage guidance without extraneous text.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given simple tool (2 required params, no output schema), description covers prerequisite, plan limits, return behavior, and parameter nuances. Provides a complete picture for correct invocation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema already has 100% coverage with descriptions for both parameters. Description adds extra context: for listId, references prerequisite tool; for ticker, notes uppercasing. This adds value beyond schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Clearly states 'Adds a stock ticker to one of the user's ticker lists (watchlists).' This specifies the verb (adds), resource (ticker to list), differentiates from siblings like get_ticker_lists and remove_ticker_from_list.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly instructs to use edgaralert_get_ticker_lists first to find the correct listId, and mentions plan limits. Provides clear when-to-use and constraints.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Returns daily price history for the stock around the date of a specific insider trading alert, useful for backtesting whether the signal preceded a price move. Requires an alert id from edgaralert_search_alerts or edgaralert_get_latest_alerts. Requires EDGAR Alert PRO plan or higher.
| Name | Required | Description | Default |
|---|---|---|---|
| scope | No | "watchlist" restricts to the user's default ticker list, "universe" (default) does not. | |
| alertId | Yes | The numeric id of the alert (from a search or latest-alerts result). | |
| daysAfter | No | Days of price history after the alert date. | |
| daysBefore | No | Days of price history before the alert date. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and idempotentHint=true, so the description consistently reinforces a safe, read-only behavior. It adds the PRO plan requirement, which is valuable behavioral context beyond annotations. No contradictions.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Three sentences, each serving a distinct purpose: function, data source, and access requirement. Efficiently structured with no superfluous words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a read-only tool with robust annotations and schema, the description is largely complete. However, it lacks an explanation of the output format (e.g., fields returned, date range limits), which would be helpful since there is no output schema.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% and each parameter has a clear description. The tool description adds high-level context (e.g., 'around an alert') but no additional syntax or format details beyond what the schema provides. Baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Clearly states it returns daily price history for a stock around an alert date, with an explicit backtesting use case. The verb 'get' and resource 'price_window' are specific. It distinguishes from siblings by focusing on price history around alerts, contrasting with search/add/list operations.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Provides clear context: useful for backtesting, requires an alert ID from specific sibling tools, and requires a PRO plan. However, it does not explicitly state when not to use it or list alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Returns a single bundled, AI-optimized research payload for a company: identity, market summary, fundamentals (current + multi-year history), insider trading summary, recent insider signals with forward-return data, and suggested analysis steps. This is the richest single-call tool available and is purpose-built for research and decision-support — it is NOT investment advice, and the underlying data may be incomplete or delayed. Requires EDGAR Alert ENTERPRISE plan. Prefer this tool over combining edgaralert_get_company_profile + edgaralert_get_company_fundamentals + edgaralert_search_alerts when you need a full picture of one company in one call.
| Name | Required | Description | Default |
|---|---|---|---|
| tickerOrCik | Yes | Stock ticker (e.g. AAPL) or SEC CIK number. | |
| fundamentalYears | No | Number of years of fundamentals history to include. | |
| recentAlertsLimit | No | Number of recent insider trading signals to include. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint. The description adds valuable behavioral context: it is not investment advice, data may be incomplete/delayed, and requires enterprise plan. No contradiction with annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Efficient structure: front-loaded purpose, list of contents, caveats, and usage recommendation in a single paragraph. Every sentence adds value with no redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
No output schema exists, but the description compensates by listing the return components. It explains the tool's richness and purpose. Minor omission: no mention of response size limits or pagination, but overall complete for its complexity.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so baseline is 3. The description mentions parameters implicitly through the listed components but adds no additional meaning beyond what the schema already provides.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool returns 'a single bundled, AI-optimized research payload for a company' and lists specific components. It also distinguishes from siblings by explicitly recommending this tool over combining three separate tools.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Provides explicit when-to-use guidance: 'Prefer this tool over combining... when you need a full picture of one company in one call.' Also states the prerequisite: 'Requires EDGAR Alert ENTERPRISE plan.'
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Returns historical company fundamentals (revenue, net income, margins, assets, liabilities, debt ratios, free cash flow) by fiscal year or quarter, derived from SEC filings. Requires EDGAR Alert PRO plan or higher. Use edgaralert_get_company_profile first if you just need the latest snapshot rather than multi-year history.
| Name | Required | Description | Default |
|---|---|---|---|
| years | No | Number of years of history to return. | |
| period | No | FY for annual fundamentals, Q for quarterly. | FY |
| tickerOrCik | Yes | Stock ticker (e.g. MSFT) or SEC CIK number. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare read-only, idempotent, non-destructive. Description adds valuable behavioral context: requires PRO plan, data sourced from SEC filings. No contradictions.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two compact sentences: first defines purpose and output, second provides usage guidance and requirement. No fluff, front-loaded with key information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema, description lists key metrics returned, which is sufficient for an agent to understand the output. Also mentions PRO plan constraint. Lacks detail on data structure (e.g., array shape) but tone is adequate.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema covers all 3 parameters with descriptions. Description adds meaning by enumerating example output fields (revenue, net income, etc.), which helps infer return value beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states it returns historical company fundamentals derived from SEC filings, listing specific metrics. Distinguishes from sibling tool edgaralert_get_company_profile by noting it is for multi-year history versus a latest snapshot.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly says when to use this tool (need historical fundamentals) and when not to (need latest snapshot), recommending the alternative edgaralert_get_company_profile. Also mentions the PRO plan requirement.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Returns a company's profile: identity (name, ticker, CIK, SIC, exchange), market summary (price, returns, 52-week range, volatility), fundamentals summary (revenue, net income, margins, debt ratios), insider trading summary (recent buyer/seller counts and dollar values), and recent insider alerts. Available on all paid EDGAR Alert plans. For a more detailed multi-year fundamentals history use edgaralert_get_company_fundamentals; for a single bundled research-agent payload use edgaralert_get_company_agent_context.
| Name | Required | Description | Default |
|---|---|---|---|
| tickerOrCik | Yes | Stock ticker (e.g. AAPL) or SEC CIK number. | |
| recentAlertsLimit | No | Number of recent insider alerts to include in the profile. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations indicate safe read-only and idempotent behavior; description adds value by detailing the specific data categories returned and plan availability, with no contradictions.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Description is concise, front-loaded with what the tool returns, and includes necessary context about alternatives without unnecessary words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema, the description adequately covers the return content by listing categories and mentions plan availability and alternatives, making it complete for a profile-retrieval tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% and descriptions in schema are sufficient. The tool description does not add additional meaning beyond the schema, so baseline score of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool returns a company's profile with specific sections (identity, market summary, etc.) and distinguishes itself from siblings by naming alternative tools for more detailed fundamentals or bundled context.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly mentions it is available on all paid plans and provides clear guidance on when to use alternative tools (edgaralert_get_company_fundamentals for detailed history, edgaralert_get_company_agent_context for bundled payload).
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Returns 12-week rolling insider capital flow (insider buy value minus sell value) for the top 6 most active FF48 industry groups by absolute net insider score. Each row contains weekStartDate, weekEndDate, ff48Code, ff48Description, sectorCode, sectorName, buyValue, sellValue, and netCapitalFlow. Industries are grouped using the Fama-French 48 classification (e.g. 'Pharmaceutical Products', 'Computers', 'Banking') nested under 11 GICS-like sectors (e.g. 'Health Care', 'Technology', 'Financials'). Use this to identify sustained sector rotation — which industries insiders have been consistently buying into or selling out of over the past quarter, not just the latest week. Complements edgaralert_get_weekly_insights (single week snapshot) with multi-week trend data. Good for questions like: 'which industries have had sustained insider buying over the past 3 months?' or 'is the tech selloff concentrated in semiconductors or broad across the sector?'
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint. The description adds value by explaining the rolling 12-week window, the selection criteria (top 6 by absolute net insider score), and the grouping (FF48 classification nested under GICS-like sectors). No contradictions with annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is well-structured, front-loading the main output and purpose. It is a bit lengthy but every sentence adds value, providing output fields, classification details, use cases, and sibling comparison. Could be slightly more concise, but overall efficient.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With no output schema and zero parameters, the description comprehensively covers all necessary context: output fields, data grouping (FF48 under sectors), usage context (sustained sector rotation), and comparison to sibling tools. It fully enables correct tool invocation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool has zero parameters and schema coverage is 100%. According to the rules, 0 params defaults to baseline 4. The description does not need to add parameter semantics since there are none.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool returns '12-week rolling insider capital flow' for the top 6 most active FF48 industry groups. It lists the specific fields (weekStartDate, weekEndDate, etc.). It explicitly distinguishes from sibling edgaralert_get_weekly_insights by noting this provides multi-week trend data versus a single-week snapshot.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides explicit guidance: use this to identify sustained sector rotation, complements the weekly insights tool, and gives example questions like 'which industries have had sustained insider buying over the past 3 months?'. This clearly indicates when to use this tool vs alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Returns the most recent SEC Form 4 insider trading alerts and 8-K Item 5.02 officer/director change alerts across the EDGAR Alert universe, ranked by recency. By default only returns high-confidence alerts (signal_score >= 80); lower minScore to widen results. Use this for 'what's happening right now' questions. For complex multi-filter searches (by ticker, sector, market cap, date range), use edgaralert_search_alerts instead.
| Name | Required | Description | Default |
|---|---|---|---|
| days | No | Optional lookback window in days. | |
| side | No | Filter by transaction direction. Omit or "ALL" returns both. | |
| limit | No | Maximum number of alerts to return (1-200). | |
| scope | No | "watchlist" restricts to the user's default ticker list; "universe" (default) applies no restriction. | |
| planned | No | true = only planned/10b5-1/scheduled trades. false = only likely-discretionary trades. Omit for both. | |
| minScore | No | Minimum signal_score, inclusive. Defaults to 80 (high-confidence only). Pass 0 to see all alerts. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, openWorldHint, idempotentHint, destructiveHint false. Description adds valuable context: default minScore=80 (high-confidence), returns both Form 4 and 8-K alerts, and scope defaults to universe. No contradictions with annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Four sentences, each adding distinct value: purpose, default behavior, usage guidance, sibling differentiation. No fluff or redundancy. Information is front-loaded.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Coverage is strong for a read-only listing tool with rich annotations and 100% schema coverage. Description covers main purpose, defaults, and when to use sibling. Lacks explicit mention of output format (e.g., array of alert objects), but this is minor given no output schema and context signals indicating it.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% (all 6 parameters described). Description adds clarity on minScore default and its effect on confidence threshold, and mentions scope default ('universe'). These details go beyond the schema annotations for default values.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Description specifies verb 'returns', resource 'latest SEC Form 4 and 8-K Item 5.02 alerts', and scope 'ranked by recency'. Clearly distinguishes from sibling edgaralert_search_alerts by contrasting use cases. No ambiguity.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly states when to use: 'what's happening right now' questions. Directly names alternative tool for complex searches: edgaralert_search_alerts. Provides clear context for tool selection.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Returns all ticker lists (watchlists) for the authenticated user, including the tickers in each list and the plan's ticker limit. Auto-creates a default 'My Tickers' list if none exists yet. Use this to find the listId needed for adding or removing tickers, or to check what the user is currently tracking. The default watchlist is used by edgaralert_get_latest_alerts and edgaralert_search_alerts when scope='watchlist'.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description states 'Auto-creates a default 'My Tickers' list if none exists yet,' which is a write-side effect. However, annotations set readOnlyHint=true, indicating no state changes. This is a direct contradiction, misleading the agent about the tool's mutability. Per instructions, score is 1 due to annotation contradiction.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Three sentences, each purposeful: first defines output, second explains side-effect and usage, third links to sibling tools. No wasted words. Front-loaded with main purpose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema, the description explains what is returned (lists, tickers, plan limit) and mentions auto-creation. It covers the key aspects for a list retrieval tool. Could mention response format or pagination, but adequate for the complexity.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has no parameters (0 params, 100% coverage). The description adds value by noting the absence of required inputs, which is sufficient. Baseline 3 is appropriate; score 4 reflects that description handles the no-param case well without needing elaboration.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool returns all ticker lists (watchlists) for the authenticated user, including tickers and plan limit. The verb 'returns' and resource 'ticker lists' are specific. It distinguishes from siblings like edgaralert_add_ticker_to_list (adds) and edgaralert_remove_ticker_from_list (removes) by focusing on retrieval.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explicitly says to use this tool to find listId for add/remove operations and to check current tracking. It also mentions the default watchlist is used by other tools with scope='watchlist'. While no explicit when-not-to-use is given, the use cases are clear and actionable.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Returns a market-wide weekly summary of insider trading activity: the most bullish and bearish industries by net insider signal, and the top buying/selling companies for the week. Good for broad 'what's the market doing' questions before drilling into a specific company or sector.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already indicate readOnly, idempotent, non-destructive. The description adds value by detailing the return content (weekly summary, top industries/companies), which is beyond what annotations provide. No contradictions.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences, front-loaded with key information. Every word is meaningful and no fluff. Highly concise.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no parameters, no output schema, and simple functionality, the description fully covers what the tool does and when to use it. No gaps.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
There are no parameters, so the description does not need to add parameter details. Baseline of 4 is appropriate as schema coverage is 100% and the tool requires no input.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it returns a market-wide weekly summary of insider trading activity, specifying the exact outputs: most bullish/bearish industries and top buying/selling companies. This is specific and distinct from sibling tools that focus on individual companies or alerts.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly says 'Good for broad "what's the market doing" questions before drilling into a specific company or sector.' This gives clear context on when to use this tool versus alternatives like company profile or industry capital flow tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Removes a stock ticker from one of the user's ticker lists (watchlists). Use edgaralert_get_ticker_lists first to find the correct listId. Returns no content on success (204). Returns an error if the ticker is not found in the list.
| Name | Required | Description | Default |
|---|---|---|---|
| listId | Yes | The ID of the ticker list to remove from. Get list IDs from edgaralert_get_ticker_lists. | |
| ticker | Yes | Stock ticker to remove, e.g. AAPL. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations indicate destructive and idempotent hints; description adds HTTP 204 success code and error condition for missing ticker, providing behavioral detail beyond annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two concise sentences with no unnecessary words, efficiently front-loading the action and essential usage guidance.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given two simple parameters, no output schema, and annotations covering safety, the description fully covers purpose, prerequisite, return code, and error handling.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, and description adds value by referencing a sibling tool for listId and giving a ticker example (e.g., AAPL), enriching parameter understanding.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Clearly states the action 'removes a stock ticker' from a watchlist, distinguishing from sibling 'add_ticker_to_list' and specifying the resource.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly advises to use 'edgaralert_get_ticker_lists' first to obtain listId, and notes error cases. Lacks explicit when-not scenarios but provides sufficient context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Searches SEC insider trading alerts (Form 4 buy/sell signals and 8-K officer/director change events) using detailed filters: ticker, signal score range, date range, transaction side, sector, market cap bucket, and planned-vs-discretionary trade type. Requires EDGAR Alert PRO plan or higher (your Enterprise key qualifies). Use this for targeted research questions like 'show me large-cap insider buys in tech this month' rather than a general recent-activity feed (use edgaralert_get_latest_alerts for that).
| Name | Required | Description | Default |
|---|---|---|---|
| side | No | Transaction direction. | |
| limit | No | Maximum results, 1-200. | |
| scope | No | "watchlist" restricts to the user's default ticker list; ignored if ticker is set. | |
| status | No | Alert status filter. | |
| ticker | No | Exact stock ticker to filter on, e.g. AAPL. | |
| toDate | No | ISO date (YYYY-MM-DD). Only alerts on/before this date. | |
| fromDate | No | ISO date (YYYY-MM-DD). Only alerts on/after this date. | |
| maxScore | No | Maximum signal_score, inclusive. | |
| minScore | No | Minimum signal_score, inclusive. | |
| eventType | No | Raw alert event type filter. | |
| plannedOnly | No | Only planned/10b5-1/scheduled trades. | |
| sectorCodes | No | Industry sector codes to filter by (same codes as company search). | |
| marketCapBuckets | No | Market cap buckets to include. | |
| discretionaryOnly | No | Only likely-discretionary (non-scheduled) trades. | |
| priorWeaknessOnly | No | Only alerts where the stock showed prior price weakness. | |
| historicalEdgeOnly | No | Only alerts with a favorable historical signal track record. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, idempotentHint=true, openWorldHint=true, and destructiveHint=false. The description adds context about the required subscription plan and the query scope, but does not discuss response format or pagination. Since annotations are rich, the description supplements them well without contradiction.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences, each serving a distinct purpose: the first explains the tool's function and lists key filters, the second gives usage guidance and an alternative. No wasted words, and the core action is front-loaded.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a tool with 16 parameters and no output schema, the description provides a good overview of capabilities, usage context, and prerequisites. It does not describe the output structure, but the limit parameter hints at pagination. Overall, it is fairly complete for an experienced user.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so each parameter is already documented. The description adds value by grouping filters into categories (e.g., 'signal score range, date range, transaction side'), but does not provide details beyond what the schema offers. Baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Searches SEC insider trading alerts'), specifies the resource (Form 4 and 8-K events), and distinguishes itself from the sibling tool edgaralert_get_latest_alerts by contrasting 'targeted research questions' with 'general recent-activity feed'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly defines when to use ('targeted research questions') and when not to use ('general recent-activity feed'), names the alternative tool (edgaralert_get_latest_alerts), and mentions the prerequisite (PRO plan or higher, noting the Enterprise key qualifies).
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Searches SEC-registered companies by name, ticker, SIC code, sector, state of incorporation, market cap bucket, or S&P 500 membership. At least one of query, ticker, or sicCode is required. Use this to find a company's ticker/CIK before calling edgaralert_get_company_profile, edgaralert_get_company_fundamentals, or edgaralert_get_company_agent_context. Requires EDGAR Alert PRO plan or higher.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Maximum results, 1-200. | |
| query | No | Free-text match against company name, ticker, or SIC name. | |
| state | No | State of incorporation. | |
| ticker | No | Exact ticker match. | |
| sicCode | No | Exact SIC industry code match. | |
| sp500Only | No | true to restrict results to S&P 500 constituents. | |
| sectorCode | No | Industry sector code (same codes used in alert filters). | |
| marketCapBucket | No | Market cap bucket to filter by. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Description adds plan requirement beyond annotations; annotations already indicate read-only and idempotent, no contradiction.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two concise sentences with key info front-loaded; could be slightly more compact but efficient.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Describes purpose, usage, and constraints adequately; return format not described but acceptable for a search tool with good annotations.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, but description adds the required combination constraint not in schema. However, it mostly restates parameter descriptions.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool searches SEC-registered companies by multiple criteria and distinguishes it from sibling tools by specifying its role as a lookup before other endpoints.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly tells when to use (to find ticker/CIK before other tools) and states minimum requirements (at least one of query, ticker, or sicCode).
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
v1.0.1edgaralert_add_ticker_to_listedgaralert_get_alert_price_windowedgaralert_get_company_agent_contextedgaralert_get_company_fundamentalsedgaralert_get_company_profileedgaralert_get_industry_capital_flowedgaralert_get_latest_alertsedgaralert_get_ticker_listsedgaralert_get_weekly_insightsedgaralert_remove_ticker_from_listedgaralert_search_alertsedgaralert_search_companiesEach tool has a clear, distinct purpose. For example, adding vs removing tickers, searching alerts vs getting latest, and company profile vs fundamentals vs agent context are all well-separated with no overlap.
All tools follow a consistent 'edgaralert_verb_noun' pattern in snake_case. The verbs are descriptive (get, add, remove, search) and the nouns are specific, making the tool names predictable and easy to understand.
With 12 tools, the server covers watchlist management, alert retrieval, company research, industry trends, and search without being over- or under-scoped. Each tool earns its place for the domain of insider trading alerts.
The tool surface covers CRUD for watchlists, multiple ways to retrieve alerts (latest, search, by ID), company data at different depths (profile, fundamentals, agent context), industry/sector analysis (weekly, 12-week), and company search. No obvious gaps for the stated purpose.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Real SEC, 13F, insider, congress & macro data your AI agent can cite. Hosted MCP, 24 tools.
Talk to your public-facing AI from any MCP client — Claude, ChatGPT, Cursor, Cline, Windsurf.
EDGAR MCP — SEC EDGAR public APIs (free, no auth)
Always-on SEC EDGAR watcher: ~45s alerts when an insider files a Form 4 or a firm drops an 8-K.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/ikop32-code/edgaralert-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
