The Seitrace Insights MCP Server provides natural-language access to Seitrace Insights API through a resource-based Model Context Protocol interface with five core tools:
• Discover Resources: List available resources like insights_address, insights_erc20, insights_erc721, insights_native, and general_faucet
• List Actions: Enumerate available actions for specific resources
• Fetch Schemas: Retrieve JSON Schema for resource actions to understand required input parameters
• Invoke Actions: Execute resource actions with validated payloads to retrieve insights data or manipulate resources
• Generate Code Snippets: Create language-specific code examples (JavaScript, Python, Node.js, Java) for programmatic integration
Key Features:
Input validation with clear error messaging
Secure API key handling via environment variables (SECRET_APIKEY)
Integration with MCP-compatible clients like VS Code extensions (Continue, Cline)
Self-describing architecture for discoverability
Developer faucet access for testing
Communication over stdio with MCP clients
Generates JavaScript code snippets for interacting with blockchain APIs
Required runtime environment for executing the MCP server
Used for package management and quick deployment via npx
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., "@Seitrace Insights MCP Server show me the token info for USDC on Pacific-1"
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.
The essential MCP (Model Context Protocol) server for the Sei blockchain.
Five tools that form the resource-based interface (use in order 1→2→3→4):
list_resources — list available resources (start here)
list_resource_actions — list actions for a resource
get_resource_action_schema — REQUIRED get the JSON Schema for an action before invoking
invoke_resource_action — invoke an action with payload matching the schema
get_resource_action_snippet — (optional) generate a code snippet to perform a resource action in the specified language
Supported resources
General
general_faucet - enable requesting faucet for developers
general_rpc_lcd - enable general rpc/lcd inquiries for the agents, and execute the rpc/lcd requests based on the demands
general_associations — query hybrid associations (EOA/assets/txs) across EVM and native Sei. Returns simplified pointer/pointee fields when applicable.
Insights
insights_address — Query address data: details, transactions, token transfers.
insights_erc20 — Query ERC-20 tokens: info, balances, transfers, holders.
insights_cw20 — Query CW20 tokens: info, balances, transfers, holders.
insights_native — Query native tokens: info, transfers, balances, holders.
insights_ics20 — Query ICS20 tokens: info, transfers, balances, holders.
insights_erc721 — Query ERC-721 tokens: info, holders, instances, balances, transfers.
insights_erc1155 — Query ERC-1155 tokens: info, holders, instances, balances, transfers.
insights_cw721 — Query CW721 tokens: info, instances, balances, holders, transfers.
insights_smart_contract — Query smart contract details.
insights_assets — Search official assets by name/symbol/identifier and get asset details by identifier. Uses Sei gateway endpoints; search is performed offline over the fetched assets list.
insights_earnings — Search/list earnings pools (APR/APY) for pacific-1 and fetch a pool by address. Returns simplified fields: name, address, url, image, provider, tvl, apr, apy.
insights_transactions — Query transaction details by hash via gateway (pacific-1, atlantic-2, arctic-1).
Smart Contract
smart_contract — Query smart contract state via Multicall3, search verified contracts, or download smart contract ABI from Seitrace (pacific-1, atlantic-2, arctic-1).
Related MCP server: SEI MCP Server V2
Make sure you obtain an API Key for free here
Check installation guide
What MCP provides to end users and assistants:
Natural‑language access to Seitrace insights. The assistant performs API calls on your behalf.
Self‑describing tool flow: enumerate actions, retrieve the input schema, then invoke.
Input validation and clear error messages using per‑action JSON Schemas.
Concise discovery: minimal list output; detailed payloads only when invoking actions.
Integration with MCP‑enabled VS Code extensions (e.g., Continue, Cline).
Simple, secure API key handling via environment variables (sent as x-api-key).
Quick start via npx: npx -y @seitrace/mcp.
Using the MCP SDK, drive the resource-based flow via the five tools. Important: Always follow this sequence, especially step 3:
// 1) Discover available resources
const resources = await client.callTool({ name: 'list_resouces', arguments: {} });
// -> { resources: ['erc20', 'erc721', 'native', ...] }
// 2) List actions for a resource
const actions = await client.callTool({
name: 'list_resouce_actions',
arguments: { resource: 'insights_erc20' },
});
// -> { resource: 'erc20', actions: [{ name, description }, ...] }
// 3) **REQUIRED** Get the JSON Schema for a specific action
// This step is critical - parameter names in descriptions may differ from actual schema
const schema = await client.callTool({
name: 'get_resource_action_schema',
arguments: { resource: 'insights_erc20', action: 'get_erc20_token_info' },
});
// -> { resource: 'insights_erc20', action: 'get_erc20_token_info', schema }
// The schema reveals exact parameter names like "q" instead of "query", "chain" instead of "chain_id", etc.
// 4) Invoke the action with payload matching the schema structure
const res = await client.callTool({
name: 'invoke_resource_action',
arguments: {
resource: 'insights_erc20',
action: 'get_erc20_token_info',
payload: { chain: 'pacific-1', contract_address: '0x...' },
},
});
// res.content[0].text -> "API Response (Status: 200):\n{ ... }"
// 5) Optionally, generate a code snippet for an action
const snippet = await client.callTool({
name: 'get_resource_action_snippet',
arguments: { resource: 'insights_erc20', action: 'get_erc20_token_info', language: 'node' },
});
// -> { resource, action, language, snippet }The server validates payload against the action’s schema and returns a pretty-printed JSON body when applicable.
Node.js 20+
A Seitrace Insights API key (optional for discovery, required for most live calls), obtain it here
npm installCopy .env.example to .env and set your values as needed.
Environment variables:
API_BASE_URL (optional) — defaults to https://seitrace.com/insights
SECRET_APIKEY — Seitrace API key; used to set header x-api-key
# Type-check and compile to build/
npm run build
# Run the MCP server over stdio (used by MCP clients)
npm startThis server is designed to be launched by an MCP-compatible client (e.g., via a command/args configuration). It communicates over stdio.
Run the E2E to verify the root resource flow and (optionally) a live positive-call:
# Optionally provide your API key so the positive path runs
SEITRACE_API_KEY=your_key_here npm run test:e2eMake sure you run our e2e test to see the common errors we covered.
E2E: npm run test:e2e (optional E2E_DEBUG=1 for [E2E] logs).
Node: Use v20+.
Keep tools/list output compact. Do not embed per-action details there—fetch them via getResourceActionSchema.
New endpoints should appear under the correct resource; root tool methods should provide discovery and invocation consistently.
Prefer small, focused modules in src/lib/ for shared logic.
See LICENSE
Please shoot emails to dev@cavies.xyz
Get the JSON Schema for a specific resource action.
| Name | Required | Description | Default |
|---|---|---|---|
| action | Yes | ||
| resource | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It states the tool retrieves a JSON Schema but does not specify whether this is a read-only operation, if it requires authentication, what happens on errors (e.g., invalid resource/action), or the format of the returned schema. This leaves critical behavioral traits unclear for a tool that likely interacts with system resources.
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 a single, clear sentence that directly states the tool's function without any unnecessary words. It is front-loaded and efficiently conveys the core purpose, making it easy to parse and understand quickly.
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 the tool's complexity (involves specific resources and actions) and the lack of annotations, output schema, and schema descriptions, the description is incomplete. It does not address key contextual aspects like error handling, return format, or dependencies on other tools (e.g., needing to list resources first). For a tool that likely returns structured data, more detail is needed to ensure proper use.
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 0% description coverage, so the parameters 'resource' and 'action' are undocumented in the schema. The description mentions 'specific resource action' but does not add meaning beyond this, such as examples of valid resources/actions, their formats, or where to find them. This fails to compensate for the schema's lack of documentation, leaving parameters ambiguous.
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's purpose with a specific verb ('Get') and resource ('JSON Schema for a specific resource action'), making it immediately understandable. However, it does not explicitly differentiate from sibling tools like 'get_resource_action_snippet' or 'list_resource_actions', which might also involve resource actions, leaving some ambiguity about its unique role.
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 no guidance on when to use this tool versus alternatives. It does not mention prerequisites, such as needing to know the resource and action names beforehand, or contrast it with siblings like 'list_resource_actions' (which might list available actions) or 'invoke_resource_action' (which might execute an action). This lack of context could lead to misuse.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Generate a code snippet to perform a resource action in the specified language. For example, a JavaScript snippet to call the action with the required parameters.
| Name | Required | Description | Default |
|---|---|---|---|
| action | Yes | ||
| language | Yes | ||
| resource | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of behavioral disclosure. It mentions generating a code snippet but doesn't cover critical aspects such as whether this is a read-only operation, if it requires authentication, potential rate limits, error handling, or the format of the output. For a tool with no annotation coverage, this leaves significant gaps in understanding its behavior.
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 concise and front-loaded, stating the core purpose in the first sentence. The second sentence provides a helpful example without unnecessary elaboration. However, it could be slightly more structured by explicitly separating parameter explanations, but overall, it avoids waste and is appropriately sized for the tool's complexity.
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 the tool's complexity (3 parameters, no annotations, no output schema), the description is incomplete. It lacks details on output format, error cases, dependencies on other tools (e.g., needing to list resources first), and behavioral traits. Without annotations or an output schema, the description should provide more context to fully guide an AI agent, but it falls short.
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 0%, meaning the schema provides no descriptions for parameters. The description adds minimal semantics by mentioning 'resource, action, and target language' and listing supported languages in the schema, but it doesn't explain what 'resource' or 'action' refer to, their expected formats, or how they interact. This insufficient detail fails to compensate for the low schema coverage.
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's purpose: 'Generate a code snippet to perform a resource action in the specified language.' It includes a specific verb ('Generate') and resource ('code snippet'), and the example adds clarity. However, it doesn't explicitly differentiate from sibling tools like 'invoke_resource_action' or 'get_resource_action_schema', which is why it doesn't achieve a perfect score.
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 no guidance on when to use this tool versus alternatives. It mentions an example but doesn't specify contexts, prerequisites, or exclusions relative to siblings like 'invoke_resource_action' (which might execute actions directly) or 'get_resource_action_schema' (which might provide schema details). This lack of comparative guidance limits its utility for an AI agent.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Invoke a resource action with a payload matching its schema.
| Name | Required | Description | Default |
|---|---|---|---|
| action | Yes | ||
| payload | Yes | ||
| resource | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It fails to disclose behavioral traits: it doesn't indicate if this is a read/write operation, what permissions are needed, potential side effects (e.g., data modification), error handling, or response format. The phrase 'invoke' suggests an action execution but lacks details on consequences or safety, leaving critical gaps for an agent.
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 a single, efficient sentence with no wasted words. It is front-loaded and directly addresses the core function, though it lacks depth. While concise, it under-specifies rather than being overly verbose, earning a high score for structure but not full marks due to missing essential details.
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 the complexity (3 parameters with nested objects, no annotations, no output schema), the description is incomplete. It doesn't explain what 'invoke' entails, the nature of resources/actions, expected outcomes, or error cases. Without annotations or output schema, the agent lacks crucial information to use the tool effectively, making this inadequate for a general-purpose action 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 description coverage is 0%, so the description must compensate. It mentions 'payload matching its schema,' which adds minimal context about 'payload' but doesn't explain 'resource' or 'action' parameters. With 3 undocumented parameters and no enums, the description fails to provide meaningful semantics beyond what the bare schema (types and required fields) already offers.
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 'Invoke a resource action with a payload matching its schema' restates the tool name ('invoke_resource_action') and title (null) without specifying what 'invoke' means in practice or what types of actions/resources are involved. It distinguishes from siblings like 'get_resource_action_schema' by implying execution rather than retrieval, but remains vague about the actual purpose beyond basic verb+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?
No guidance is provided on when to use this tool versus alternatives. The description mentions 'payload matching its schema,' which hints at using 'get_resource_action_schema' first, but this is not explicit. There are no exclusions, prerequisites, or clear context for choosing this over sibling tools like 'list_resource_actions' or 'get_resource_action_snippet.'
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List actions for a given resource.
| Name | Required | Description | Default |
|---|---|---|---|
| resource | Yes | Resource name. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of behavioral disclosure. It states 'List actions' but doesn't describe what an 'action' entails (e.g., operations, permissions, or workflows), how results are returned (e.g., pagination, format), or any limitations (e.g., rate limits, authentication needs). For a tool with zero annotation coverage, this leaves significant gaps in understanding its behavior.
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 a single, efficient sentence: 'List actions for a given resource.' It's front-loaded with the core purpose, has zero wasted words, and is appropriately sized for a simple tool. Every part of the sentence contributes directly to understanding the tool's function.
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 the lack of annotations and output schema, the description is incomplete for a tool that lists actions. It doesn't explain what 'actions' are, how they're structured, or what the return value looks like. For a tool with 1 parameter and no structured output information, more context is needed to fully understand its operation and results.
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%, with the parameter 'resource' documented as 'Resource name.' in the schema. The description adds no additional meaning beyond this, such as examples of valid resource names or how they relate to actions. Since the schema already provides basic documentation, the baseline score of 3 is appropriate, but no extra value is added.
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 'List actions for a given resource' clearly states the verb ('List') and resource ('actions'), but it's vague about what 'actions' means in this context. It doesn't distinguish from siblings like 'list_resources' (which lists resources rather than actions) or 'get_resource_action_schema' (which gets schema details rather than listing). The purpose is understandable but lacks specificity about the nature of these actions.
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?
No guidance is provided on when to use this tool versus alternatives. The description doesn't mention prerequisites, context for selecting this over siblings like 'list_resources' or 'invoke_resource_action', or any constraints. Without such information, the agent must infer usage from tool names alone, which is insufficient for optimal selection.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List available resources (e.g., insights_erc20, insights_erc721, insights_native).
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden for behavioral disclosure. The description only states what the tool does at a high level ('List available resources') but provides no information about what the listing returns (format, structure, completeness), whether there are limitations (pagination, rate limits), or what permissions might be required. For a tool with zero annotation coverage, this is insufficient behavioral context.
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 a single, efficient sentence that gets straight to the point. The parenthetical examples are well-placed and add useful context without unnecessary elaboration. There's zero wasted space - every word serves a purpose in clarifying what the tool does.
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 zero-parameter listing tool with no output schema, the description provides adequate basic information about what the tool does. However, it lacks important context about what the listing returns (format, structure) and how it relates to sibling tools. The examples help, but without annotations or output schema, more behavioral detail would be beneficial for a complete understanding.
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 0 parameters with 100% description coverage, so the schema already fully documents that no arguments are required. The description appropriately doesn't waste space discussing parameters that don't exist. The examples provided ('insights_erc20, insights_erc721, insights_native') give helpful context about what types of resources might be listed, which adds value beyond the empty parameter 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?
The description clearly states the verb ('List') and resource ('available resources'), and provides concrete examples of what types of resources might be listed. However, it doesn't explicitly differentiate from sibling tools like 'list_resource_actions' - both involve listing, so the distinction between 'resources' and 'resource actions' could be clearer.
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 no guidance on when to use this tool versus alternatives. With sibling tools like 'list_resource_actions' that also perform listing operations, there's no indication of when this tool is appropriate versus when other listing tools should be used. No prerequisites, exclusions, or alternative recommendations are mentioned.
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.
v1.0.0get_resource_action_schemaget_resource_action_snippetinvoke_resource_actionlist_resource_actionslist_resourcesEach tool has a clearly distinct purpose with no overlap: list_resources enumerates available resources, list_resource_actions enumerates actions for a resource, get_resource_action_schema retrieves schema details, get_resource_action_snippet generates code, and invoke_resource_action executes the action. The descriptions clearly differentiate their functions, eliminating any ambiguity.
All tool names follow a consistent verb_noun pattern using snake_case, with verbs like 'get', 'list', and 'invoke' paired with descriptive nouns (e.g., 'resource_action_schema', 'resource_action_snippet'). This uniformity makes the set predictable and easy to understand.
With 5 tools, the set is well-scoped for a server focused on resource action management. Each tool serves a specific role in the workflow (listing, schema retrieval, snippet generation, invocation), and none feel redundant or missing, making the count appropriate for the domain.
The tool surface provides complete coverage for interacting with resource actions: listing resources and their actions, retrieving schemas and code snippets, and invoking actions. This covers the full lifecycle from discovery to execution, with no apparent gaps for the server's purpose.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Query real-time blockchain token data across EVM and Solana networks. Access token balances, transfers, prices, holders, NFT ownership, DEX swaps, and liquidity pools. Supports Ethereum, Base, Arbitrum, BSC, Polygon, Solana, and more.
Blockchain analytics API for AI agents. Smart Money signals, wallet profiling, token analytics.
Blockchain analytics API for AI agents. Smart Money signals, wallet profiling, token analytics.
Explore blockchain data across addresses, tokens, blocks, and transactions. Investigate any transa…
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/Seitrace/seitrace-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
