MCP server for Context7 - provides documentation and code examples for libraries and frameworks
Context7 MCP server provides 2 tools with reasonable naming conventions and clear descriptions. Both tools follow verb_noun patterns (query-docs, resolve-library-id) and include parameter descriptions. However, output schemas are not documented in the provided source, parameter validation constraints are minimal, and error handling guidance is absent. The server targets a specialized use case (documentation lookup) with read-only operations, which mitigates some risk but limits overall capability maturity.
Query documentation for a specific library using a Context7-compatible library ID and user query. Returns formatted code snippets and information snippets from the library's documentation.
Resolves a package/product name to a Context7-compatible library ID and returns matching libraries. Must be called before 'Query Documentation' tool to obtain a valid Context7-compatible library ID unless the user explicitly provides a library ID in the format '/org/project' or '/org/project/version'. Returns library information including name, description, code snippet count, source reputation, benchmark score, and available versions.
Output schemas not documented. Tool descriptions explain what is returned ('formatted code snippets and information snippets', 'library information including name, description...') but no formal JSON Schema is provided for response structure. LLMs cannot reliably extract fields or plan downstream steps without documented output schemas.
No input validation constraints. The 'libraryId' parameter accepts format '/org/project' or '/org/project/version' as a string, but no JSON Schema enum, pattern, or constraint is visible to enforce this. The 'query' parameter has no length limits or validation rules. Agents may pass malformed IDs or extremely long queries.
No error handling guidance. Tool descriptions do not explain what happens on failure (e.g., 'If libraryId is invalid, the server returns...') or how to recover. Agents cannot self-correct when a lookup fails.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-22 | C | 69 | 2026-07-28+ | v2 |
| 2026-03-09 | F | 40 | - | v1 |
Missing dependency documentation. resolve-library-id's description correctly notes 'Must be called before Query Documentation tool to obtain a valid Context7-compatible library ID unless the user explicitly provides...' However, query-docs does not acknowledge this relationship or guide agents on when to call resolve-library-id first.
Parameter descriptions lack format/constraint detail. 'User's documentation query or question' does not specify expected length, language, or complexity. 'Package or library name' does not hint whether partial matches or typo tolerance is supported.