A
licenseNot graded
qualityC
maintenanceMCP server providing RAG context and failure capture for Claude Code, enabling semantic search across project knowledge and storing/analyzing failures.
1
MIT
failmodes-mcp
by elyngved
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., "@failmodes-mcpsearch for failure modes related to hallucination"
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.
failmodes-mcp
MCP server for the Fail Modes taxonomy — a machine-readable knowledge base of AI system failure modes.
Provides four tools over 100+ canonical failure mode records spanning factuality, alignment, planning, code generation, instruction following, and more.
Tools
Tool | Description |
| Search by symptom text or keyword phrase. Returns ranked matches. |
| Retrieve the full structured record for a failure mode by ID slug. |
| List all taxonomy categories with descriptions and mode counts. |
| List all modes, optionally filtered by category ID. |
Related MCP server: hive-exp
Quick Start
No installation required — run directly with npx:
npx failmodes-mcpConfiguration
Claude Desktop
Add to ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows):
{
"mcpServers": {
"failmodes": {
"command": "npx",
"args": ["-y", "failmodes-mcp"]
}
}
}Cursor / VS Code
Add to your MCP settings file:
{
"mcpServers": {
"failmodes": {
"command": "npx",
"args": ["-y", "failmodes-mcp"]
}
}
}Remote (no install required)
A hosted Streamable HTTP version is also available — no npm package needed:
{
"mcpServers": {
"failmodes": {
"url": "https://www.failmodes.com/api/mcp"
}
}
}How It Works
On first tool call, the server fetches current taxonomy data from failmodes.com and caches it in memory for the duration of the session. Requires internet access.
The stdio transport makes this compatible with any MCP client that supports running local processes (Claude Desktop, Cursor, VS Code, etc.).
Links
Taxonomy source: github.com/elyngved/failmodes-taxonomy
Website: failmodes.com
Remote MCP manifest: failmodes.com/server.json
License
MIT
Available Tools
4 toolsget_failure_modeAInspect
Retrieve the full structured record for a single failure mode by its ID slug (e.g. 'citation-hallucination', 'sycophancy').
ParametersJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | The failure mode ID slug, e.g. 'citation-hallucination' |
TDQS
A4.1/5.0
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It states it retrieves a 'full structured record' but does not disclose behavior for missing IDs, error handling, or any side effects. For a simple read operation, this is acceptable but not fully transparent.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence, no wasted words. Perfectly concise for the tool's simplicity.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness5/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the simple tool structure (1 required parameter, no output schema, no nested objects), the description is complete. It tells what it returns and how to invoke it. No additional information is necessary.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema already has 100% coverage with a description for the single 'id' parameter. The description repeats the example but adds no new meaning beyond the schema. Baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Retrieve'), the resource ('full structured record for a single failure mode'), and the identifier ('by its ID slug'). This distinguishes it from sibling tools like list_categories or search_failure_modes, which operate on collections or use search.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage when you have a specific ID slug and want a single record. It does not explicitly state when not to use it (e.g., for listing all modes), but the context from sibling tools and the wording 'by its ID slug' provides adequate guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
list_categoriesAInspect
List all taxonomy categories with their IDs, names, descriptions, and mode counts.
ParametersJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
TDQS
A3.6/5.0
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided; description does not disclose auth needs, performance, pagination, or side effects. Only states what it lists.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence, front-loaded with verb and resource, no wasted words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
No output schema; description covers return fields adequately. Lacks details on ordering or error cases but sufficient for a simple list-all tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Zero parameters, schema coverage 100%; description adds value by specifying returned fields (IDs, names, descriptions, mode counts). Baseline 4 for 0 params.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states it lists all taxonomy categories with specific fields (IDs, names, descriptions, mode counts). Distinguishes from siblings like get_failure_mode and list_modes which deal with failure modes.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this vs siblings. Could mention scenarios like getting an overview or before drilling into specific categories.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
list_modesAInspect
List failure modes, optionally filtered to a single category by category ID.
ParametersJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| category | No | Optional category ID to filter by, e.g. 'factuality'. Omit to list all modes. |
TDQS
A3.9/5.0
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so the description carries the burden. It discloses basic behavior (list and filter) but omits details like pagination, sorting, or read-only nature. For a simple list tool, this is minimally adequate but could be more explicit.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, well-structured sentence with no unnecessary words. It conveys the essential information efficiently.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's simplicity (1 optional param, no output schema, no annotations), the description covers the basic functionality. However, it does not hint at the return format or structure of the output, which could be helpful for an AI agent.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100% for the single parameter. The description adds value by providing an example value ('factuality'), which helps the agent understand the expected format beyond the schema's generic description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
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 'failure modes', and specifies optional filtering by category ID. It distinguishes from sibling tools like get_failure_mode (single item) and search_failure_modes (search) by indicating a straightforward listing operation.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies when to use (listing modes, optionally filtered) but does not explicitly contrast with siblings like search_failure_modes or get_failure_mode. No guidance on when not to use or prerequisites.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
search_failure_modesAInspect
Search the Fail Modes taxonomy by symptom text or keyword phrase. Returns ranked matches with id, name, category, and matched context.
ParametersJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| symptom | Yes | Symptom phrase or keyword to search for, e.g. 'made up a citation' or 'refused to help after pushback' |
TDQS
A3.5/5.0
Behavior2/5
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 traits. The description only states it searches and returns results, but it does not explicitly disclose that this is a read-only operation with no side effects. For a search tool, this is generally safe, but the lack of explicit safety guarantees (e.g., 'read-only') reduces transparency. There is no mention of authentication, rate limits, or potential impacts.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely concise: two sentences with no wasted words. The first sentence states action and input, the second states output structure. It is front-loaded and efficient.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's simplicity (one parameter, no output schema, no annotations), the description covers the essential purpose and output. However, it omits details such as whether the search is case-insensitive, supports partial matches, or how ranking is determined. For a minimal viable description, it is adequate but not thorough.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema description coverage is 100%, and the parameter 'symptom' has a detailed enum-like example in the schema itself. The tool description adds no additional meaning beyond paraphrasing the schema's parameter description. Baseline is 3 for high coverage, and there is no extra value added.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb ('Search'), the resource ('Fail Modes taxonomy'), the input ('by symptom text or keyword phrase'), and the output ('Returns ranked matches with id, name, category, and matched context'). It distinguishes the tool from siblings like 'get_failure_mode' (which likely retrieves a single item by ID) and 'list_categories'/'list_modes' (which provide lists without search).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage for searching by symptoms or keywords, which is clear. However, it does not explicitly state when not to use this tool (e.g., when to use 'get_failure_mode' instead) or provide alternatives among siblings. The context is implied but could be more explicit to guide the AI agent away from inappropriate use cases.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
4 tool updates
v0.1.0- First observed
get_failure_mode - First observed
list_categories - First observed
list_modes - First observed
search_failure_modes
TDQS
A4.1/5.0
Disambiguation5/5
Each tool has a distinct purpose: retrieving a specific failure mode by ID, listing all categories, listing modes with optional filtering, and searching by symptom text. There is no functional overlap between them.
Naming Consistency5/5
All tool names use consistent snake_case with a verb_noun pattern (get_failure_mode, list_categories, list_modes, search_failure_modes), and the naming clearly indicates each tool's action and target entity.
Tool Count5/5
With 4 tools covering listing, retrieval, and search for a read-only taxonomy, the count is appropriate. It is neither too minimal nor excessive for the scope.
Completeness5/5
The tool set provides comprehensive coverage for a read-only failure mode taxonomy: full listing of categories, listing of modes (optionally by category), retrieval of a single mode, and keyword search. No obvious gaps for the intended use case.
Maintenance
ActivitySlowing
ResponsivenessNo issues
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Connectors
Capability registry for the agentic economy. Semantic search over verified MCP server listings.
MCP server for building and testing AI agents with multi-model experimentation and insights.
MCP server providing access to the Scorecard API to evaluate and optimize LLM systems.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceAn MCP server enabling AI agents to record, query, and share structured problem-solving experiences with human review and confidence decay.11MIT
- AlicenseNot gradedqualityAmaintenanceMCP server enabling AI assistants to explore schema.org types, generate JSON-LD examples, validate structured data, and navigate the complete ontology with fuzzy matching and caching.4321MIT
- AlicenseNot gradedqualityBmaintenanceThis MCP server provides semantic document search and retrieval, enabling AI assistants to search documents, search categories, and retrieve category hierarchies using the Model Context Protocol.2MIT
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/elyngved/failmodes-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server