agent-memory-mcp (xultrax-web/agent-memory-mcp) is an MCP server listed on the M8ven Trust Index. It scores 74 out of 100, grade C. It declares 24 tools. No publisher has claimed this listing.
Guardrails for AI coding agents that enforces rules via compliance receipts, blocking destructive actions and syncing rules across all AI tools.
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
xultrax-web
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_memorysearch_memoriesFuzzy search across name, description, and body. Tolerates typos, word-order shifts, and partial matches. Returns top matches with relevance scores (0-100) and body-context snippets. Use this for human-readable browsing.
relevant_memoriesFind memories relevant to a query and return their FULL content (not summaries). Designed for LLM ingestion — call this when the assistant needs context on a topic and the memory index alone isn't specific enough. Returns up to `max` memories as a markdown document.
get_memoryFetch a single memory by name.
list_memoriesList stored memories, optionally filtered by type and/or tags. Paginated.
delete_memoryrestore_memoryRestore a memory from .trash/ back into the active store. Picks the most recent trash entry for the name.
doctorCheck storage integrity. Reports orphan files (on disk but not indexed), dangling index entries (no file), unreadable files, and invalid types. Pass rebuild-index=true to reconstruct MEMORY.md from disk.
statsDashboard of memory-store state: counts per type, total size, largest memory, audit-log size, trash count.
rotate_keyRotate the receipt-signing key material (HMAC and/or Ed25519). Generates fresh keys and INVALIDATES every outstanding Compliance Receipt. Use after a suspected key leak — e.g. the .keyring was ever committed or synced. Optional `mode`: 'hmac' | 'ed25519' | 'both' (default 'both').
initInstall a starter guardrail pack — sensible hard/soft rules (protect main, block rm -rf, no prod data destruction, no curl|sh, flag secrets) — and emit them to every tool's companion files. Zero-config protection on day one. Pass force=true to overwrite same-named rules. Pair with `agent-memory inst…
validate_receiptValidate a CRP 1.1 (Ed25519) Compliance Receipt issued by ANOTHER agent-memory server using that server's published public key — no shared secret (the federation primitive). Checks signature, expiry, and required caveats. Pass `receipt` (object or JSON string) and `public_key` (inline PEM or a file …
log_eventsRead recent entries from the audit event log (.events.jsonl). Returns the last N events, optionally filtered by action.
verify_memoryRe-evaluate a memory's claims against signals in its content. Extracts URLs, dates, and file paths from the body; flags stale-date signals on project-type memories; returns type-specific verification heuristics for the LLM or operator to act on. Pairs with the audit_stale prompt.
find_backlinksList memories that link to the given memory via [[wiki-link]] syntax in their bodies. Useful for building a 'what references this' view.
find_relatedSurface memories related to a given one. Ranks by combining: outbound [[wiki-links]], inbound backlinks, shared tags, same type, and content similarity (name + description). Use this to navigate the memory graph by association rather than by exact lookup.
sync_statusReport the git-sync state of the memory store: remote URL, branch, local uncommitted files, commits ahead/behind origin. Use this before opening a new session to know if you have stale memories from another machine.
sync_pushCommit any local memory changes and push to the configured git remote. Auto-generates a timestamped commit message if none provided. Use at the end of a session to make memories available on your other machines.
sync_pullPull memory updates from the configured git remote (fast-forward only). Run at the start of a session to get memories saved on other machines. Refuses to pull if there are uncommitted local changes.
save_rulelist_rulesList every active rule memory with severity, scope, and staleness markers (>90 days since last_verified). Use this to audit which rules are currently constraining the agent.
auditcheck_actionemit_companionsDisclosed vulnerabilities in this server's declared npm dependencies (via OSV). Whether each is reachable depends on the installed versions.
Model Context Protocol (MCP) TypeScript SDK does not enable DNS rebinding protection by default
AGENT_MEMORY_AUTO_EMIT_DIRSet =/path/to/project and the server re-emits all four files automatically on every rule save.AGENT_MEMORY_COMPANION_DIRAGENT_MEMORY_DIR"env": { "": "/abs/path/to/memory" }AGENT_MEMORY_EMBED_MODELAGENT_MEMORY_EMBED_URLAGENT_MEMORY_LOGOperational logging is separate. Set =debuginfowarnerror (default info) and structured lines stream to stderr — won't pollute the MCP stdio channel.AGENT_MEMORY_SCOPE"env": { "": "global" }CRP_SIGNING_MODECRP 1.1 · Ed25519 asymmetric signing (set =ed25519)EDITORe opens the highlighted memory in $ (vim/notepad/nano/whatever) — saves back to diskFORCE_COLORColor output is on by default in TTYs. Set NO_COLOR=1 to disable, =1 to force-enable in pipes.GIT_AUTHOR_EMAILCommits use the identity agent-memory <agent-memory@local> by default — set / GIT_COMMITTER_EMAIL in your environment if you want per-machine attribution.GIT_AUTHOR_NAMEGIT_COMMITTER_EMAILCommits use the identity agent-memory <agent-memory@local> by default — set GIT_AUTHOR_EMAIL / in your environment if you want per-machine attribution.GIT_COMMITTER_NAMENO_COLORColor output is on by default in TTYs. Set =1 to disable, FORCE_COLOR=1 to force-enable in pipes.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
24/24 tools missing one or more hints — save_memory (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); search_memories (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); relevant_memories (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +21 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 pass
npm test failed — tests do not pass
Make sure npm test runs cleanly. Common cause: missing build step or missing env vars.
Shell command execution
2 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, 1 high severity in production deps — @modelcontextprotocol/sdk@1.0.4 (high)
Run npm audit fix, or upgrade the affected packages to a non-vulnerable version.
Dependency freshness
3/7 production deps abandoned (no release in 2+ years): proper-lockfile@2022-06-24 (4.1y), gray-matter@2023-07-12 (3y), ink-text-input@2024-05-21 (2.2y)
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/xultrax-web/agent-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