The FixGraph MCP server lets you search and contribute to a community-verified database of 25,000+ technical fixes across software, vehicles, home systems, and appliances.
Search for fixes (fixgraph_search): Query by error message, symptom, or technology name, with optional category filtering and configurable result limits (1–20 results)
Retrieve detailed fixes (fixgraph_get_fixes): Get all verified fixes for a specific issue by its ID or slug, including step-by-step resolution details
Submit new fixes (fixgraph_submit_fix): Contribute a fix to an existing issue, including title, root cause, ordered steps (with optional code snippets), risk level, and validation instructions — requires an API key
Report new issues (fixgraph_submit_issue): Document a newly discovered problem in the database — requires an API key
Verify fixes (fixgraph_verify_fix): Record whether a fix worked in your environment, contributing to the community trust scoring system
Searching is free with no API key; submitting fixes or issues requires a free API key obtainable via a simple registration endpoint.
Search and contribute to FixGraph — 25,000+ community-verified fixes for real-world technical errors across software, vehicles, home systems, and appliances — directly from any MCP-compatible AI assistant.
Tool | Description |
| Search by error message, symptom, or technology |
| Get all verified fixes for a specific issue |
| Submit a new fix (requires API key) |
| Submit a new issue your agent discovered (requires API key) |
| Record whether a fix worked in your environment |
Related MCP server: Cache Overflow
Add to your MCP config:
{
"mcpServers": {
"fixgraph": {
"command": "npx",
"args": ["-y", "fixgraph-mcp"]
}
}
}Search is free with no API key. To submit fixes or issues, add your key:
{
"mcpServers": {
"fixgraph": {
"command": "npx",
"args": ["-y", "fixgraph-mcp"],
"env": {
"FIXGRAPH_API_KEY": "fg_live_..."
}
}
}
}Register instantly — no OAuth, no waiting:
curl -X POST https://fixgraph.netlify.app/api/developers/register \
-H "Content-Type: application/json" \
-d '{"name": "my-agent", "email": "you@example.com"}'Or visit fixgraph.netlify.app/developers.
Once installed, ask your AI assistant:
"Search FixGraph for Docker container exits immediately"
"Find fixes for npm ERESOLVE dependency conflict"
"Check if there is a verified fix for ERR_OSSL_EVP_UNSUPPORTED"
Get all verified fixes for a specific FixGraph issue by its ID or slug.
| Name | Required | Description | Default |
|---|---|---|---|
| issue_id | Yes | Issue ID or slug from a fixgraph_search result |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description bears full transparency burden. It only states 'get all verified fixes'—a read operation with no mention of side effects, authentication, rate limits, or limitations, which is insufficient for full disclosure.
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?
One sentence, 14 words, front-loaded with verb and resource. Every word earns its place. No wasted 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?
For a simple 1-parameter tool with no output schema, the description is adequate. It covers the essential purpose and input. Could be enhanced by briefly noting that an empty list is returned if no fixes exist, but this is minor.
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% with clear parameter description. The tool description adds 'by its ID or slug' but does not enrich beyond the schema's description. Baseline 3 is appropriate as schema already does the heavy lifting.
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?
'Get all verified fixes for a specific FixGraph issue by its ID or slug' clearly states the verb (get), resource (verified fixes), and input (ID/slug). It naturally distinguishes from siblings: fixgraph_search finds issues, fixgraph_submit_fix sends fixes.
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 implies usage (after obtaining an issue ID from search) but does not explicitly state when to use this tool versus alternatives, nor does it provide exclusions or prerequisites.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search FixGraph for engineering fixes. Returns matching issues with trust scores and fix counts.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Number of results (1–20, default 5) | |
| query | Yes | Error message, technology, or symptom to search for | |
| category | No | Optional category filter (e.g. "databases", "networking") |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must carry the full burden. It only mentions returning data but does not disclose auth requirements, rate limits, or whether it is read-only. This is insufficient for a search tool.
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 sentence that is clear and front-loaded. Every word is necessary and earns its place.
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?
The complexity is moderate (3 parameters, no output schema, no annotations), but the description is minimal. It lacks details on return format, sorting, pagination, or error behavior.
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 adds no additional meaning beyond the schema for parameters; it only mentions output characteristics (trust scores and fix counts).
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 searches FixGraph for engineering fixes and returns specific data (trust scores and fix counts). It distinguishes itself from sibling tools like fixgraph_get_fixes and fixgraph_submit_fix by focusing on search.
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 does not explicitly state when to use this tool versus alternatives. While the purpose implies search, there is no guidance on exclusions or when to choose a sibling tool.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Submit a new fix to FixGraph. Requires FIXGRAPH_API_KEY env var.
| Name | Required | Description | Default |
|---|---|---|---|
| steps | Yes | Ordered fix steps | |
| title | Yes | Short title for the fix | |
| issue_id | Yes | Issue ID to attach the fix to | |
| risk_level | No | Risk level of applying the fix | |
| root_cause | Yes | Why the issue occurs | |
| validation | No | How to verify the fix worked |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden but only states 'Submit a new fix' and the env var requirement. It lacks disclosure of side effects, idempotency, error behavior, or any behavioral traits beyond the basic action.
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 sentence plus a short prerequisite note, front-loaded with the action, and contains no unnecessary words. Every part is essential.
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 6 parameters, no output schema, and no annotations, the description is too sparse. It does not explain return values, error conditions, or the submission process, leaving the agent with significant 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?
Schema coverage is 100% with each parameter having a description. The description adds no additional parameter-specific meaning, so 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 'Submit a new fix to FixGraph' clearly states the action (submit) and resource (fix), and combined with sibling tool names (get_fixes, search), it effectively distinguishes this tool's creation purpose from retrieval or querying.
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 mentions the prerequisite env var but does not provide explicit guidance on when to use this tool versus alternatives like fixgraph_get_fixes or fixgraph_search. No when-not or explicit context for selection is given.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Each tool has a distinct purpose: searching for issues, retrieving fixes for a specific issue, and submitting a new fix. There is no overlap or ambiguity.
Tools follow the 'fixgraph_<verb>' pattern, but 'fixgraph_search' lacks a noun after the verb while the others include one. This minor inconsistency does not impede readability.
With only three tools, the set is slightly thin but appropriate for a focused service that allows search, retrieval, and submission of fixes. It is not under-scoped.
The tools cover basic operations (search, get, create) but lack update and delete functionality. This is a noticeable gap for full lifecycle management.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Shared knowledge base for AI agents. Search and contribute solutions to technical problems.
Structured knowledge base for AI agent solutions. Search, explore, and retrieve build logs.
AI Agent Source Registry. 288K+ curated sources for agentic search and discovery.
Open scientific and engineering knowledge for AI agents: search, evidence, document publishing.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/jawdat6/fixgraph-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server