MCP.Market

Agent Memory MCP server

by xultrax-web·io.github.xultrax-web/agent-memory-mcp·v0.15.0·1 stars
No reviews yet

Markdown memory for AI agents. Files you can read, edit, grep, and commit. Not a database.

B78/100grade B
Write a reviewInstall
What users say
No reviews yet
Be the first
Safety scan
B78/100

full report

Adoption
New

1 stars83 downloads/wk

Reviews

Write one

Nobody has reviewed Agent Memory yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Agent Memory tools (24, 1 write)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • audit

    v0.11.4 · operational health report for the rule store. Surfaces: rule count by severity, stale rules (last_verified > 90 days or null), pattern conflicts (two rules sharing an enforce_on category AND an identical regex pattern), recent check_action denials, and recent unreceipted destructive ops.

  • check_action

    v0.11.3 · the protocol enforcement point. Pass a proposed action description + its category; the server matches against rule memories (type=rule) and either:

  • delete_memorywrite action

    Move a memory to .trash/ (soft delete). The file is removed from the index but recoverable via restore_memory until you manually empty .trash/.

  • doctor

    Check 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.

  • emit_companions

    Regenerate companion rule files from the current rule memories.

  • find_backlinks

    List memories that link to the given memory via [[wiki-link]] syntax in their bodies. Useful for building a 'what references this' view.

  • find_related

    Surface 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.

  • get_memory

    Fetch a single memory by name.

  • init

    Install 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 install-hooks` so hard rules actually block tool calls.

  • list_memories

    List stored memories, optionally filtered by type and/or tags. Paginated.

  • list_rules

    List 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.

  • log_events

    Read recent entries from the audit event log (.events.jsonl). Returns the last N events, optionally filtered by action.

  • relevant_memories

    Find 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.

  • restore_memory

    Restore a memory from .trash/ back into the active store. Picks the most recent trash entry for the name.

  • rotate_key

    Rotate 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').

  • save_memory

    Save (or update) a memory. Memories are markdown files with YAML frontmatter,

  • save_rule

    Save (or update) a rule memory · the 'memory as constraint' wedge.

  • search_memories

    Fuzzy 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.

  • stats

    Dashboard of memory-store state: counts per type, total size, largest memory, audit-log size, trash count.

  • sync_pull

    Pull 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.

  • sync_push

    Commit 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_status

    Report 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.

  • validate_receipt

    Validate 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 path; the issuer gets theirs via `agent-memory export-pubkey`).

  • verify_memory

    Re-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.

Public scan report

scanner v0.1.9 · 2026-09-27 · same rubric, same numbers if you re-run it

no findings
  • Code scan3 source files scanned25/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitylocal package, no credentials required12/15
  • Maintenancelast push 92 days ago8/15
  • Maintainer identityregistry namespace matches repository owner6/10
Overall 78/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Agent Memory compares

Against every graded Databases MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
78/100
higher than 47% of 802 Databases servers
Tools
24
the typical Databases server has 8
Tools that change things
4%
typical: 10%. Fewer write tools means less an agent can break
GitHub stars
1
more than 45% of 602 Databases servers
Downloads a week
83
more than 53% of 328 Databases servers with a package

What its tools let an agent do: 18 read · 2 create · 3 change · 1 delete

Install Agent Memory in Claude Code, Cursor or VS Code

Runs npx -y @xultrax-web/agent-memory-mcp on your machine. Read the scan report first; the gateway never runs local packages.

claude mcp add agent-memory-mcp -- npx -y @xultrax-web/agent-memory-mcp
Add to Cursor

What the publisher says

From the Agent Memory repository's README, as published. We do not edit it. Read it on GitHub

agent-memory-mcp

Guardrails for AI coding agents — write the rule once, every tool obeys, destructive actions get blocked.

<!-- 30-second demo: drop the clip here once recorded → -->

Your AI coding agent will eventually try to rm -rf the wrong folder, force-push to main, or delete the file you actually needed. agent-memory-mcp is the memory layer where you write the rule once, in plain markdown — and it enforces itself:

  • Blocks destructive actions at the protocol layer. The agent proposes an action; the server checks it against your rules and either refuses it or issues a short-lived, signed Compliance Receipt it must present to act. Soft rules in a config file get ignored — this doesn't.
  • One rule, every tool. Save it once and it emits to AGENTS.md, CLAUDE.md, .cursor/rules/, and .gemini/ automatically — Claude Code, Cursor, Cline, Copilot, Gemini and Windsurf read the same rules, no plugin.
  • Plain files you own. cat it, grep it, edit it in vim, commit it to git, sync it across machines with agent-memory sync. No database, no daemon, no cloud — and if the AI gets it wrong, you fix it in a text editor.

Memory — the rules, recipes, decisions, and context that survive every session and every tool — is the substrate. Enforcement is the point. Reference implementation of the Compliance Receipt Protocol 1.0, so other MCP servers can adopt the same receipts and interoperate.

Quickstart · guarded in 60 seconds

# After adding the server to your MCP client (see Install below), from your project:
agent-memory init            # drop in a starter guardrail pack (protect main, no rm -rf, no prod-data destruction, …)
agent-memory install-hooks   # make hard rules actually BLOCK in Claude Code (soft rules → ask)

Your agent is now guarded across every tool. Write your own rules with saverule — they enforce and_ emit to AGENTS.md / CLAUDE.md / .cursor/rules / .gemini. (CLI commands assume a global install — npm i -g @xultrax-web/agent-memory-mcp — or prefix with npx -y.)

Memory as constraint · the v0.11 → v0.13 arc

What v0.10 and below shipped: a great file-based memory store. What v0.11+ added: rules that enforce themselves. A rule memory type carries severity (hard / soft), scope, applieswhen, matches regex patterns, enforceon categories, and last_verified date. From those, the server projects companion files out to every AI tool and gates destructive operations via cryptographic receipts.

1. Rule memories project to every tool

agent-memory save-rule no-emojis-ever \
  --description "Never use emojis in commits, comments, or chat output." \
  --severity hard \
  --scope global \
  --enforce-on commits,chat_responses \
  --content "No emojis. Anywhere. Ever."

agent-memory emit-companions
# writes AGENTS.md + CLAUDE.md + .cursor/rules/*.mdc + .gemini/instructions.md

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Agent Memory: common questions

Is Agent Memory MCP server safe?
Mostly: it is graded B (78/100). Read the Agent Memory safety report
How do I install Agent Memory?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Agent Memory need an API key?
No secret keys are declared. It reads 3 settings from the environment.
Is Agent Memory maintained?
The last commit was 130 days ago (2026-06-27). The latest release is v0.15.0.
What can I use instead of Agent Memory?
Servers from other publishers that do the same job: CogniCore MCP server, Magic Cloud MCP server and AnythingMCP MCP server.
How does Agent Memory compare with other Databases MCP servers?
safety score 78/100 (higher than 47% of 802 Databases servers); tools 24 (the typical Databases server has 8); tools that change things 4% (typical: 10%. Fewer write tools means less an agent can break). Full comparison.

Alternatives to Agent Memory

Same job from other publishers: the closest match first, then the best rated.

  • CogniCore
    Memory, reflection and safety for AI agents. Hosted or local, no vector database.
    A
  • Magic Cloud
    Generate secured CRUD APIs over your database, run SQL, manage files, tasks and a headless browser
    A
  • AnythingMCP
    MCP gateway and company brain: 694 connectors (SAP, ERP, SQL), file search, memory and skills.
    B
  • Microsoft Access Database
    Read and edit Microsoft Access databases (.accdb/.mdb) - forms, VBA, tables, queries. Windows.
    A
  • open-memex
    Local-first memory for AI coding agents — Markdown + SQLite FTS5, shared across editors via MCP.
    B