Thin local MCP bridge for portable ContextCanopy knowledge and personal AI authority
Context Canopy MCP provides 9 tools with complete input schemas and descriptions. Naming follows verb_noun convention (capture_from_conversation, get_agent_profile, search_knowledge). Descriptions are present and contextual (avg ~120 chars), meeting baseline minimums. However, output schemas are not documented in the source, LLMs cannot predict return structure. Parameter descriptions are adequate but lack format constraints (e.g., search_knowledge.limit has no min/max bounds). Error handling is minimal; no recovery guidance or actionable error messages visible. Security is strong (path traversal guards in safeKnowledgePath, safeKnowledgeDirectory, safeExistingMarkdown), but no tool-level permission declarations. Composition is sound, each tool has one responsibility and tools chain via IDs (e.g., get_entry accepts path, list_entries returns paths). Missing: output schema documentation, parameter constraints (enums, ranges), error recovery patterns.
Capture knowledge from conversation into the Second Brain vault with full validation and metadata enrichment
Retrieve a personal AI agent profile from the vault
Retrieve common rules for personal AI collaboration from COMMON-RULES.md
Retrieve a specific knowledge entry from the vault by relative path
Retrieve mountain context (long-term direction) from the vault
List all knowledge entries in a category or across all categories
List all available Second Brain skills from the vault
Output schemas not documented. LLMs cannot predict return structure (fields, types, pagination). Baseline requires 100% of A+ tools to have documented return types.
Parameter constraints missing. search_knowledge.limit has no min/max bounds; list_entries.category lacks enum constraint (should be: 'all'|'Experience'|'Projects'|'Technical'). Free-form strings invite hallucinated values.
No error recovery guidance. Error responses do not tell LLMs what to do next (retry, ask user, or fail). Baseline requires categorization and actionable next steps.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | D | 59 | 2026-07-28+ | v2 |
Read a specific Second Brain skill definition from the vault
Search knowledge entries by keywords with relevance ranking
No tool-level permission declarations. Tools lack scope metadata (e.g., 'read:knowledge', 'write:vault'). Baseline requires each tool to declare required permissions for least-privilege agent configuration.
Pagination not documented for list tools. list_entries and list_second_brain_skills do not expose limit/offset or return total_count. Large result sets risk context window exhaustion.