local-agent-context
A local MCP server that gives AI coding agents persistent memory and context across sessions.
Caution. Specific findings reduced this grade. They are listed on the page. 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
TomiwaPhilip
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.
store_memoryStore a new memory (project info, convention, decision, task, lesson, or note). Memories persist across sessions and are searchable. Pass workspace path for project-specific memories.
recallSearch memories by query using full-text search. Filter by type, tags, scope, or status. Pass workspace to include project-specific memories.
update_memoryUpdate an existing memory by ID. Can change title, content, tags, importance, status, or type.
delete_memoryDelete a memory by ID. By default, soft-deletes (archives). Set hard=true to permanently remove.
list_memoriesList all memories with optional filters (type, tags, scope, status). Supports pagination with limit/offset.
get_contextGet a curated workspace context briefing: project info, active tasks, conventions, recent decisions, lessons, and global preferences. Pass workspace for project-specific context.
start_sessionStart a new coding session. Auto-closes any dangling previous session. Returns the full workspace context as a briefing.
end_sessionEnd the current coding session with a summary. The summary is stored as a searchable session_summary memory for future reference.
log_decisionLog an architectural or design decision with its rationale. Stored as a high-importance decision memory.
add_lessonRecord a lesson learned — something that went wrong, a gotcha, or a best practice discovered. Stored as a lesson memory.
sync_instructionsSync the agent instruction file to installed IDEs (VS Code, Cursor). Call this after updating the server to ensure agents have the latest usage guide. Auto-detects IDE paths or accepts an explicit path.
store_resourceStore a summary of a documentation page, URL, or web resource you fetched. Persists the key takeaways so future sessions can recall them without re-fetching.
store_researchStore findings from a research investigation — questions explored, conclusions reached, and sources consulted. Prevents re-researching the same topics in future sessions.
Disclosed vulnerabilities in this server's declared npm dependencies (via OSV). Whether each is reachable depends on the installed versions.
@modelcontextprotocol/sdk has cross-client data leak via shared server/transport instance reuse
Anthropic's MCP TypeScript SDK has a ReDoS vulnerability
Model Context Protocol (MCP) TypeScript SDK does not enable DNS rebinding protection by default
WORKSPACE_PATHFallback chain: Tool workspace arg → --workspace CLI flag → env var → global-only mode.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 — store_memory (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); recall (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); update_memory (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.
Tool inputs are validated
Only 0/13 tool handlers declare input schemas (0%)
Declare an inputSchema with zod/joi/yup on every tool definition.
Tool handlers catch errors
Only 0/13 tool handlers wrap calls in try/catch (0%)
Wrap each tool handler body in try/catch and return a structured error response.
Tests exist
No test files found
Add tests that exercise each declared tool.
Shell command execution
7 child_process calls — runs shell commands
Prefer library functions over shell-outs. If you must shell out, ensure all inputs are properly escaped.
Production dependencies are patched
0 critical, 3 high severity in production deps — @modelcontextprotocol/sdk@1.12.1 (high), @modelcontextprotocol/sdk@1.12.1 (high)
Run npm audit fix, or upgrade the affected packages to a non-vulnerable version.
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/tomiwaphilip/local-agent-context)?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