# skylarng89/cogmemory-mcp

Source: https://glimind.com/server/github%2Fskylarng89%2Fcogmemory-mcp
Registry id: `github/skylarng89/cogmemory-mcp`
Status: unknown

## Tools (44)

- `add_observation`: Attach a fact to an entity
- `add_plan_item`: Add a roadmap item
- `analyze_impact`: Analyze impact of uncommitted changes (git diff) — maps changed files to symbols and computes reverse transitive caller closure
- `annotate_symbol`: Attach narrative text to a symbol or trace
- `check_for_updates`: Check if a newer version is available on npm (HTTPS GET to registry, cached 24h)
- `check_index_coverage`: Report indexed vs. unindexed vs. stale files with per-language breakdowns
- `cogmemory_status`: Show runtime config: package version, schema version, db path, workspace root, scope, index coverage, and subsystem counts
- `create_entity`: Add entity (deduped on name+type)
- `create_relation`: Link two entities with a typed relation
- `create_spec`: Store a long-form document
- `create_task`: Create a task, optionally linked to a plan
- `delete_by_key`: Delete a context entry by its string key
- `delete_by_path`: Remove a file from the code graph file_index
- `delete_item`: Delete a single row by ID from any subsystem
- `end_session`: Close session, store summary
- `find_dead_code`: Find symbols with zero inbound callers, excluding exported symbols and configurable entry points
- `find_duplicates`: Detect duplicate/clone symbol pairs via exact hash + MinHash similarity, inserts SIMILAR_TO edges
- `find_related`: Discover semantically-related symbols via shared callers/imports/same-file heuristics, inserts SEMANTICALLY_RELATED edges
- `generate_codemap`: BFS from entry symbol, bounded subgraph with optional traces + annotations
- `get_active_context`: Read current focus by key
- `get_code_snippet`: Fetch source code lines for a symbol by ID or name, with optional context padding
- `get_session_summary`: Recall session details including decisions, errors, changelog
- `get_spec`: Retrieve by ID or exact title
- `index_codebase`: Walk workspace, extract symbols + edges (JS/TS via ts-morph, Python via tree-sitter)
- `list_items`: Browse stored entries from any subsystem with optional filters
- `list_projects`: List all projects with row counts, staleness flags; active project marked
- `log_change`: Append changelog entry
- `log_error`: Record an error with signature and resolution
- `prune_projects`: Permanently delete a project and all of its rows (requires confirm=true)
- `purge_subsystem`: Remove ALL rows from a subsystem (requires confirm=true)
- `query_code_graph`: Look up a symbol's callers/callees/imports (1-hop)
- `query_graph`: Multi-hop structural graph query using recursive CTE — supports arbitrary depth, edge-type filters, direction
- `recall`: Unified search across decisions/conventions/errors/changelog
- `remember_convention`: Log/update a convention (design token, pattern, style, naming)
- `remember_decision`: Log a decision with rationale and tags
- `rename_project`: Rename a project's display label (slug is immutable)
- `search_knowledge`: Query entities, relations, observations
- `semantic_code_search`: TF-IDF based semantic code search — natural language query returns ranked symbols by relevance
- `set_active_context`: Upsert current focus/task by key
- `start_session`: Begin a work session (returns session ID)
- `switch_project`: Re-resolve the active project at runtime from a workspace root (fail-closed)
- `update_plan_status`: Change plan item status
- `update_spec`: Update content/title, auto-bumps version
- `update_task_status`: Change task status

Measured by Glimind (https://glimind.com): MCP handshake + tool list only, no tool is ever called. CC BY 4.0.