CogMemory MCP Server — Unified context subsystems for AI coding agents
Inferred from the transports this listing declares (stdio). A client not listed here hasn’t been ruled out — it just isn’t something Forge can confirm.
Verification confirms publisher identity (repo ownership), not code safety. The security scan covers known CVEs and suspicious install scripts.
Read out of the source npm actually ships, at scan time. The package was never executed. Tools registered dynamically at runtime, or hidden inside bundled or minified code, can be missed — so this is a floor on the tool surface, not a complete census of it.
get_code_snippetGet the source code lines for a symbol by ID or name. Returns the file content between start_line and end_line, with optional context padding.Get the source code lines for a symbol by ID or name. Returns the file content between start_line and end_line, with optional context padding.
No input schema was published for this tool.
check_index_coverageReport indexed vs. unindexed vs. stale files and per-language breakdowns. Use to understand how much of the workspace the code graph covers.Report indexed vs. unindexed vs. stale files and per-language breakdowns. Use to understand how much of the workspace the code graph covers.
No input schema was published for this tool.
find_dead_codeFind symbols with zero inbound structural edges (calls, imports, extends, implements). Excludes exported symbols, configurable entry-point patterns, and test files.Find symbols with zero inbound structural edges (calls, imports, extends, implements). Excludes exported symbols, configurable entry-point patterns, and test files.
No input schema was published for this tool.
query_graphMulti-hop structural graph query using recursive CTE. Start from a symbol and traverse outbound/inbound/both through edges of specified types up to max_depth. Returns nodes and paths.Multi-hop structural graph query using recursive CTE. Start from a symbol and traverse outbound/inbound/both through edges of specified types up to max_depth. Returns nodes and paths.
No input schema was published for this tool.
analyze_impactAnalyze the impact of uncommitted changes. Auto-detects changed files via `git diff`, maps them to indexed symbols, and computes the reverse transitive caller closure. Returns impacted symbols with depth and path.Analyze the impact of uncommitted changes. Auto-detects changed files via `git diff`, maps them to indexed symbols, and computes the reverse transitive caller closure. Returns impacted symbols with depth and path.
No input schema was published for this tool.
find_duplicatesFind duplicate/clone symbol pairs via exact body_hash match and MinHash similarity. Inserts SIMILAR_TO edges for pairs above threshold.Find duplicate/clone symbol pairs via exact body_hash match and MinHash similarity. Inserts SIMILAR_TO edges for pairs above threshold.
No input schema was published for this tool.
find_relatedFind semantically-related symbols using structural heuristics: shared callers, shared imports, same file, existing SIMILAR_TO edges. Inserts SEMANTICALLY_RELATED edges.Find semantically-related symbols using structural heuristics: shared callers, shared imports, same file, existing SIMILAR_TO edges. Inserts SEMANTICALLY_RELATED edges.
No input schema was published for this tool.
semantic_code_searchSemantic/meaning-based code search using TF-IDF over symbol names and source code. Returns symbols ranked by relevance to the natural-language query.Semantic/meaning-based code search using TF-IDF over symbol names and source code. Returns symbols ranked by relevance to the natural-language query.
No input schema was published for this tool.
index_codebaseWalk the workspace and extract symbols + edges. Dispatches files to the correct language analyzer automatically via the analyzer registry. Incremental by default (only re-analyzes changed files); use full=true to force complete re-index.Walk the workspace and extract symbols + edges. Dispatches files to the correct language analyzer automatically via the analyzer registry. Incremental by default (only re-analyzes changed files); use full=true to force complete re-index.
No input schema was published for this tool.
query_code_graphLook up a symbol by name, ID, or file path — returns its callers, callees, and imports (1-hop)Look up a symbol by name, ID, or file path — returns its callers, callees, and imports (1-hop)
No input schema was published for this tool.
generate_codemapBFS from an entry symbol through the code graph, returning a bounded subgraph with optional traces and annotationsBFS from an entry symbol through the code graph, returning a bounded subgraph with optional traces and annotations
No input schema was published for this tool.
annotate_symbolAttach narrative text to a symbol or execution trace (storage-only — the server never generates the text)Attach narrative text to a symbol or execution trace (storage-only — the server never generates the text)
No input schema was published for this tool.
cogmemory_statusShow runtime configuration: package version, schema version, db path, workspace root, scope, index coverage, and subsystem counts. Use this to understand the current state of CogMemory.Show runtime configuration: package version, schema version, db path, workspace root, scope, index coverage, and subsystem counts. Use this to understand the current state of CogMemory.
No input schema was published for this tool.
check_for_updatesCheck if a newer version of cogmemory-mcp is available on npm. Makes a read-only HTTPS GET to registry.npmjs.org (cached 24h). Disable with COGMEMORY_DISABLE_UPDATE_CHECK=1 or config.json disable_update_check=true.Check if a newer version of cogmemory-mcp is available on npm. Makes a read-only HTTPS GET to registry.npmjs.org (cached 24h). Disable with COGMEMORY_DISABLE_UPDATE_CHECK=1 or config.json disable_update_check=true.
No input schema was published for this tool.
create_entityAdd an entity to the knowledge graph (deduped on name+type)Add an entity to the knowledge graph (deduped on name+type)
No input schema was published for this tool.
create_relationLink two entities with a typed relationLink two entities with a typed relation
No input schema was published for this tool.
add_observationAttach a fact/observation to a knowledge graph entityAttach a fact/observation to a knowledge graph entity
No input schema was published for this tool.
search_knowledgeQuery the knowledge graph: entities, relations, and observations by name, type, or textQuery the knowledge graph: entities, relations, and observations by name, type, or text
No input schema was published for this tool.
list_itemsBrowse stored entries from any CogMemory subsystem (sessions, decisions, conventions, errors, context, changelog, plan, tasks, entities, relations, observations, specs, symbols, edges, execution_traces, codemap_annotations, file_index). Returns rows with optional filters.Browse stored entries from any CogMemory subsystem (sessions, decisions, conventions, errors, context, changelog, plan, tasks, entities, relations, observations, specs, symbols, edges, execution_traces, codemap_annotations, file_index). Returns rows with optional filters.
No input schema was published for this tool.
delete_itemprivilegedDelete a single row by ID from any CogMemory subsystem that uses an integer primary key. For 'context' use delete_by_key; for 'file_index' use delete_by_path.Delete a single row by ID from any CogMemory subsystem that uses an integer primary key. For 'context' use delete_by_key; for 'file_index' use delete_by_path.
No input schema was published for this tool.
delete_by_keyprivilegedDelete a context entry by its string keyDelete a context entry by its string key
No input schema was published for this tool.
delete_by_pathprivilegedRemove a file from the code graph file_indexRemove a file from the code graph file_index
No input schema was published for this tool.
purge_subsystemRemove ALL rows from a single subsystem (and cascaded dependents). Requires confirm=true. Use with care — this is irreversible.Remove ALL rows from a single subsystem (and cascaded dependents). Requires confirm=true. Use with care — this is irreversible.
No input schema was published for this tool.
remember_decisionLog a decision with rationale and optional tagsLog a decision with rationale and optional tags
No input schema was published for this tool.
remember_conventionLog or update a convention (design token, pattern, style, naming)Log or update a convention (design token, pattern, style, naming)
No input schema was published for this tool.
log_errorRecord an error with its signature, description, and resolutionRecord an error with its signature, description, and resolution
No input schema was published for this tool.
set_active_contextSet or update the current active context (upsert by key)Set or update the current active context (upsert by key)
No input schema was published for this tool.
get_active_contextRead the current value of a context keyRead the current value of a context key
No input schema was published for this tool.
log_changeAppend an entry to the changelog (what happened)Append an entry to the changelog (what happened)
No input schema was published for this tool.
recallUnified search across decisions, conventions, errors, and changelog by text, tags, session, or date rangeUnified search across decisions, conventions, errors, and changelog by text, tags, session, or date range
No input schema was published for this tool.
add_plan_itemAdd a roadmap/plan itemAdd a roadmap/plan item
No input schema was published for this tool.
update_plan_statusUpdate the status of a plan itemUpdate the status of a plan item
No input schema was published for this tool.
create_taskCreate an actionable task, optionally linked to a plan itemCreate an actionable task, optionally linked to a plan item
No input schema was published for this tool.
update_task_statusUpdate the status of a taskUpdate the status of a task
No input schema was published for this tool.
start_sessionBegin a new work session (returns session ID)Begin a new work session (returns session ID)
No input schema was published for this tool.
end_sessionClose a work session and optionally store a summaryClose a work session and optionally store a summary
No input schema was published for this tool.
get_session_summaryRecall what happened in a previous session, including its decisions, errors, and changelog entriesRecall what happened in a previous session, including its decisions, errors, and changelog entries
No input schema was published for this tool.
create_specStore a long-form document (PRD, SRS, design doc), optionally linked to a knowledge graph entityStore a long-form document (PRD, SRS, design doc), optionally linked to a knowledge graph entity
No input schema was published for this tool.
get_specRetrieve a spec by ID or exact titleRetrieve a spec by ID or exact title
No input schema was published for this tool.
update_specUpdate a spec's content, title, or entity link (auto-bumps version)Update a spec's content, title, or entity link (auto-bumps version)
No input schema was published for this tool.
40 of 40 tools published a description.
Tool names and descriptions are written by the publisher and shown verbatim as inert text. They are the strings an MCP client passes to a model, so Forge scans them for prompt-injection patterns — any finding appears with the security scan above. “Privileged” is a keyword match on the tool name, not an audit of what the tool does: a benign-sounding name can still do anything.
CogMemory MCP Server — Unified context subsystems for AI coding agents
Linked names open Forge’s index of every entry observed exposing that tool. Browse all indexed tools.
The crawl stopped at the 60-package limit. The rest of the tree was never resolved.
36 more resolved packages are not drawn here (display cap: 24). Every dependency carrying an advisory is drawn regardless of the cap. Full inventory (CycloneDX SBOM)
70 declared dependencies never landed in the tree. They are missing from Forge's resolution, not from the package.
+58 more not listed. The counts by reason above cover all of them.
Not followed: peerDependencies. This tree covers runtime dependencies only, so anything those pull in was never resolved.