Memory MCP
Persistent knowledge base for AI tools: store coding rules, project context, and decisions once, then let any MCP-compatible client read them via a single endpoint.
Warning. Serious findings were identified. Review the full report before connecting. 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
theamargupta
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.
save_memoryStore a new memory with content, category, tags, and optional project scope.
search_memorySemantic search across all memories using natural language query. Uses AI-powered vector similarity.
list_memoriesBrowse memories by category, tags, project, or date range.
get_memoryRetrieve a specific memory by ID.
update_memoryModify title, content, tags, or category of an existing memory. PATCH semantics — omitted fields are left unchanged.
delete_memoryRemove a memory (soft delete — can be undone).
get_rulesFetch all 'rule' category memories — shortcut for .claude.md style rules. Optionally filter by project.
get_contextFetch all memories for a specific project — instant project onboarding.
Disclosed vulnerabilities in this server's declared npm dependencies (via OSV). Whether each is reachable depends on the installed versions.
Next.js has a Middleware / Proxy bypass in App Router applications via segment-prefetch routes
Next.js has a Middleware / Proxy bypass in App Router applications via segment-prefetch routes - Incomplete Fix Follow-Up
Next.js has a Middleware / Proxy bypass in Pages Router applications using i18n
Next.js has a Middleware / Proxy bypass through dynamic route parameter injection
Next.js Vulnerable to Denial of Service with Server Components
NEXT_PUBLIC_APP_URLNEXT_PUBLIC_SUPABASE_ANON_KEYNEXT_PUBLIC_SUPABASE_URLSUPABASE_SERVICE_ROLE_KEYTool 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
8/8 tools missing one or more hints — save_memory (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); search_memory (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); list_memories (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +5 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.
Destructive tools are labelled
2 tools perform destructive updates without destructiveHint — update_memory overwrites at line 231 (supabase); delete_memory overwrites at line 263 (supabase)
Add destructiveHint:true to any tool whose handler calls .delete(), .upsert(), .update(), unlink, rm, DELETE, DROP, REPLACE INTO, or any operation that overwrites existing data.
Descriptions match behaviour
4 tools describe read intent but their handlers mutate — search_memory (line 16: supabase.from('memory_access_log').insert({); get_memory (line 16: supabase.from('memory_access_log').insert({); get_rules (line 16: supabase.from('memory_access_log').insert({)
Rename the tool, rewrite the description, or move the side-effect into a separate clearly-named tool.
Tool handlers catch errors
Only 0/8 tool handlers wrap calls in try/catch (0%)
Wrap each tool handler body in try/catch and return a structured error response.
License file
No license file
Add a LICENSE file (MIT, Apache-2.0, etc.).
Tests exist
No test files found
Add tests that exercise each declared tool.
Production dependencies are patched
0 critical, 7 high severity in production deps — next@16.2.3 (high), next@16.2.3 (high)
Run npm audit fix, or upgrade the affected packages to a non-vulnerable version.
Dependency freshness
1/16 production deps stale: server-only@2022-09-03 (3.8y)
Tool description accuracy
4 tools have description/behavior mismatches: search_memory: description implies read-only but handler writes/deletes/executes; list_memories: description implies read-only but handler writes/deletes/executes; get_rules: description implies read-only but handler writes/deletes/executes
Update tool descriptions to accurately reflect all capabilities — especially write, delete, or execute operations.
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/theamargupta/memory-mcp)?variant=verified from the 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