MCP.Market

Agence MCP server

by l-agence·io.github.l-agence/agence·v1.0.0·4 stars
No reviews yet

AI governance MCP server — policy enforcement, skills, memory, multi-LLM consensus

C62/100grade C
Write a reviewInstall
What users say
No reviews yet
Be the first
Safety scan
C62/100

full report

Adoption
New

4 stars

Reviews

Write one

Nobody has reviewed Agence yet.

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

Agence tools (10, 2 write)

write = sends, deletes, buys or posts

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

  • guard_check

    Check a command against AIPOLICY.yaml and return the guard decision (tier, approved/denied, reason). Every command an agent runs should pass through this gate first.

  • guard_classify

    Classify a command's AIPOLICY tier without logging to the ledger. Returns JSON with tier (T0-T3), action, and matched rule.

  • ledger_status

    Show the Merkle-chained audit ledger status — entry count, chain validity, last entry.

  • ledger_verify

    Verify the Merkle chain integrity of the audit ledger. Returns OK if chain is valid, or reports the first broken link.

  • memory_recall

    Query memories by tags across all COGNOS tiers. Returns ranked results by importance × recency.

  • memory_retain

    Store a memory row in one of the 5 COGNOS tiers. Memory is persistent and queryable.

  • memory_stats

    Show memory statistics across all COGNOS tiers — row counts per store.

  • peers_runwrite action

    Run multi-LLM consensus (3 independent LLMs). Skills: solve, review, analyze, plan. Returns weighted aggregate of findings, confidence scores, and reasoning from each peer.

  • skill_list

    List all available agence skills with their groups and descriptions.

  • skill_runwrite action

    Execute an agence skill command (e.g. ^fix, ^review, ^design, ^hack). Dispatches to the appropriate agent based on skill type and routing rules.

Public scan report

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

1 high
  • Code scan32 source files scanned13/25
  • –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 139 days ago8/15
  • Maintainer identityregistry namespace matches repository owner7/10

Findings (1)

  • highShell command built from a string (injection risk)exec.shell-concat
    lib/ledger.ts: … if (!existsSync(SHARD_LEDGER)) { execSync(`touch "${SHARD_LEDGER}"`, { cwd: SHARD_DIR }); …
Overall 62/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Agence compares

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

Safety score
62/100
higher than 18% of 4,460 AI and agents servers
Tools
10
the typical AI and agents server has 6
Tools that change things
20%
typical: 0%. Fewer write tools means less an agent can break
GitHub stars
4
more than 77% of 2,711 AI and agents servers

What its tools let an agent do: 8 read · 2 change

Install Agence in Claude Code, Cursor or VS Code

Runs npx -y @l-agence/mcp-server-agence on your machine. Read the scan report first; the gateway never runs local packages.

claude mcp add agence -- npx -y @l-agence/mcp-server-agence
Add to Cursor

What the publisher says

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

l'Agence — Agentic Engineering Co-Environments

Author: Stephane Korning · 2026 · MIT + Commons Clause Version: v1.0.0 · May 2026

The governance layer for AI coding agents.

Every agent action classified, gated, and cryptographically logged — regardless of which LLM or tool runs it.

The Problem

Your AI coding agents can write code. They can commit, push, delete, refactor.

But who's watching them?

Claude Code has no audit trail. Aider trusts the user. Codex sandboxes everything and hopes for the best. LangChain gives you building blocks but no guardrails.

Agence exists because advisory guardrails aren't guardrails at all. It's the layer that sits between any AI agent and your filesystem and says "not without approval."

What Agence Does

Agence is an agent-agnostic governance stack for software engineering. It doesn't replace your coding agent — it governs, orchestrates, and audits all of them from a single control plane.

Command Gating — Every shell command is classified before execution:

Unknown commands default to T2. Not T0. Fail-closed. The guard runs as a separate process — agents cannot bypass their own policy.

Cryptographic Audit — Every agent decision is logged to a Merkle-chained, append-only ledger. Each entry links to the previous via SHA-256. Tamper with one entry and the chain breaks. Verify with: agence ^ledger verify.

Multi-Agent Orchestration — 18 agents across 4 types (persona, tool, loop, ensemble). Route with @agent syntax. Override models with dot-notation: @ralph.gpt4o. Dispatch to Aider, Claude Code, Copilot, or your own tools — all governed by the same policy.

Peer Consensus — Route any question to 3 independent LLMs and get weighted consensus. Your architecture review shouldn't depend on one model's blind spots.

Session Persistence — Save, resume, and hand off sessions between agents. Full context survives restarts. Automatic tmux capture of stdout/stdin/stderr — no 16KB buffer limits.

Git-Native — No database. No server. State lives in git worktrees and flat files. Knowledge is sharded, gated, and selectively routed — you decide what gets shared.

By the Numbers

Who This Is For

  • Teams using multiple AI coding agents who need one policy governing all of them
  • Enterprises requiring audit trails for AI-generated code changes
  • Security-conscious developers who want fail-closed gating, not fail-open trust
  • Anyone who's had an AI agent break something and wished there was a layer between the agent and rm -rf

Who This Is NOT For

  • If you want an AI pair programmer → use Aider
  • If you want IDE autocomplete → use Continue or Copilot
  • If you want to build any kind of agent → use LangChain/LangGraph
  • If you want cloud-hosted async tasks → use OpenAI Codex

Agence governs all of the above.

GitHub Action — Agence Guard

Shortened. The full README is on GitHub.

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

Agence: common questions

Is Agence MCP server safe?
With care: it is graded C, so read the findings first (62/100). Read the Agence safety report
How do I install Agence?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Agence need an API key?
No secret keys are declared. It reads 1 setting from the environment.
Is Agence maintained?
The last commit was 177 days ago (2026-05-11). The latest release is v1.0.0.
What can I use instead of Agence?
Servers from other publishers that do the same job: Basic Memory MCP server, PaperBanana MCP server and Pm Claude Skills MCP server.
How does Agence compare with other AI and agents MCP servers?
safety score 62/100 (higher than 18% of 4,460 AI and agents servers); tools 10 (the typical AI and agents server has 6); tools that change things 20% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.

Alternatives to Agence

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

  • Basic Memory
    Local-first knowledge management with bi-directional LLM sync via Markdown files.
    B
  • PaperBanana
    Generate academic diagrams and statistical plots from text using multi-agent AI.
    A
  • Pm Claude Skills
    1310 professional Agent Skills + workflow recipes — searchable & fetchable over MCP.
    A
  • IWE (iwe.md)
    Markdown knowledge base as agent memory. Runs against the notes directory it is started in.
    A
  • Memanto
    MCP server for Memanto - persistent semantic memory for any MCP-compatible agent
    A