knowledge-graph
Long-term memory system for AI agents that accumulates domain expertise through mentorship, automatically recalls relevant knowledge, and supports memory decay and growth with anti-fabrication.
Emerging. No concerning findings. Grades remain capped until the project builds reputation through adoption. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.
How we verified
Verified is a snapshot. Live keeps it current, and builds your track record.
⚡ Connect GitHub → continuous verification on every pushwhy connect →Who stands behind it
ChenLiangChong
Source: Glama
Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find. Or connect your repo for our deepest verification, Live Monitored: read-only, revoke anytime. What we access →
Install from
The grade above is for the source repository. Registries can serve a different version, so we mark the ones we were not able to read.
These names and descriptions are the publisher's own, read from the source code. We print them as written. Our assessment is the findings above, not this list.
record_experienceRecord a workflow experience (success, failure, or lesson) with steps.
recall_experienceFind past experiences by context (genre, bpm, key, mood, element).
store_knowledgeStore a knowledge node in the graph. Auto-generates embedding and FTS index.
connect_knowledgeCreate a causal edge between two knowledge nodes.
forget_knowledgeMark a knowledge node as expired (soft delete). Does not physically delete.
memory_statsGet statistics about the knowledge graph.
maintain_graphRun maintenance operations on the knowledge graph: prune weak edges, find duplicates, validate edges, find orphan nodes.
crystallize_skillCheck if KG has knowledge not yet reflected in skill md files. Reports unsynced knowledge that needs to be added to existing skills, or suggests creating new md files if content doesn't fit anywhere.
search_memorySearch the knowledge graph using hybrid search (vector + keyword + graph expansion).
get_knowledgeFetch full details for specific knowledge nodes by ID. Use after search_memory(compact=true) to expand selected results.
traverse_graphTraverse the knowledge graph from a starting node, following causal edges.
list_knowledgeList knowledge nodes by filters. Use for browsing/listing instead of search_memory (which is for relevance-ranked search).
update_knowledgeUpdate an existing knowledge node in-place. Preserves node ID and all edges. Auto-updates FTS and vector index.
Disclosed vulnerabilities in this server's declared npm dependencies (via OSV). Whether each is reachable depends on the installed versions.
uuid: Missing buffer bounds check in v3/v5/v6 when buf is provided
Tool annotations
No tools have read-only/destructive annotations
Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.
All four hints declared on every tool
13/13 tools missing one or more hints — record_experience (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); recall_experience (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); store_knowledge (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +10 more. OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.
For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.
Tests exist
No test files found
Add tests that exercise each declared tool.
Claim the listing to review these findings one by one and send us a correction where you disagree, straight to the team. Claiming also means we tell you when the grade moves, and reach you first if we find anything urgent.
[](https://m8ven.ai/mcp/chenliangchong/knowledgegraph)?variant=verified to the badge URL.Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.
https://m8ven.ai/api/mcp/tool-check