Mandare MCP server
com.mandarelabs/mandare·v0.1.0Verify an agent fleet's tamper-evident ledger, check budgets, kill a runaway agent. Local-first.
0 stars120 downloads/wk
Reviews
Write oneNobody has reviewed Mandare yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
Mandare tools (9, 1 write)
write = sends, deletes, buys or postsRead from the package source without running it. The installed server may list more.
mandare_budget_statusPer-mandate spend from the ledger: settled and reserved amounts (integer micro-units of the
mandare_certifyBuild the selective-disclosure integrity certificate (chain valid · witnessed · anchored) a
mandare_gateway_healthRead the running gateway door /healthz (halted state, card rail, witness gating). Requires
mandare_issue_mandateIssue an owner-signed mandate (SD-JWT VC) for an agent: spend caps in WHOLE currency units
mandare_issue_passportIssue an Agent Delegation Credential (SD-JWT VC) for a NEW agent: owner + local attestation
mandare_issue_tokenMint a short-lived proof-of-possession token an agent presents to the gateway (TTL ≤ 30
mandare_killwrite actionThe LOCAL, offline, fail-closed kill: revoke ONE agent, ONE mandate (the agent survives, the
mandare_reinstateReverse an agent kill (enabled by MANDARE_MCP_ALLOW_REINSTATE=1). New tokens are honored
mandare_verifyVerify the local ledger: hash chain, door signatures, RFC 6962 tree head, spend trail and
Public scan report
scanner v0.1.10 · 2026-10-01 · same rubric, same numbers if you re-run it
- Code scan10 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 0 days ago15/15
- Maintainer identityregistry namespace matches repository owner7/10
How Mandare compares
Against every graded AI and agents MCP server, from our own scans and uptime checks. Updated after each scan run.
- Safety score
- 91/100
- higher than 88% of 4,460 AI and agents servers
- Tools
- 9
- the typical AI and agents server has 6
- Tools that change things
- 11%
- typical: 0%. Fewer write tools means less an agent can break
- Downloads a week
- 120
- more than 67% of 1,538 AI and agents servers with a package
What its tools let an agent do: 8 read · 1 change
Install Mandare in Claude Code, Cursor or VS Code
Runs npx -y @mandarelabs/mcp-server on your machine. Read the scan report first; the gateway never runs local packages.
claude mcp add mandare -- npx -y @mandarelabs/mcp-server
What the publisher says
From the Mandare repository's README, as published. We do not edit it. Read it on GitHub
Mandare
Give your agents a budget they cannot talk their way out of.
Mandare is the accountability stack for AI agent fleets: signed agent identity (Passport), signed machine-readable authority (Mandate), a tamper-evident ledger of what agents actually did (Ledger), an offline kill switch — and external witnessing + public anchoring so ledger history cannot be truncated or rewritten without detection (with the witness on separate infrastructure, not even by the operator — the solo compose stack runs everything on one host and says so). Local-first: raw activity never leaves your machine.
Replay of the captured Demo 1 run — the same script CI executes and asserts on every push. Regenerate: node scripts/render-demo-gif.mjs.
Quickstart — 3 commands, no API keys needed
git clone https://github.com/mandarelabs/mandare && cd mandaredocker compose up -d --waitdocker compose run --rm demoThe demo releases a runaway agent loop against your gateway. The €20/day mandate kills it mid-run: 23 calls settle €19.17, call #24's reservation would cross €20 and is refused 403 PERDAYEXCEEDED, the refusal is itself a ledger entry, and mandare verify proves chain VALID, counters == replay(ledger), and the witnessed head history covers the chain. Dashboard at http://127.0.0.1:8788. Real providers: put keys in .env (docs).
When you're done, docker compose down -v removes the containers and the demo volumes (mandare-data, mandare-witness-state).
No docker:
./install.shpnpm demo(pnpm demo runs a cheaper model and raises the gateway's default 60 calls/minute velocity limit so the budget is the only limit in play: 71 calls, call #72 refused at the same €20 cap. The docker demo above runs the stack's real defaults.)
Proofs, not data
Raw prompts and responses never leave your machine. What crosses a trust boundary is only ever a proof: salted tree heads to the witness, an integrity certificate to an auditor, a revocation bitstring to a verifier.
agent (any SDK, base URL → the door)
│ RFC 9421-signed request (passport) or scoped PoP token
▼
┌──────────────── gateway door ────────────────┐
│ kill-check → policy (mandate: caps/window/ │ ┌─ witness (external) ─┐
│ scope/approval) → INTENT entry (reserves │────▶│ salted head history, │
│ cost in the ledger tx) → provider → RESULT │ acks│ consistency-enforced,│
│ entry (settles true cost) │◀────│ public anchor (OTS) │
└───────────────┬──────────────────────────────┘ └──────────────────────┘
▼
append-only ledger (SQLite/Postgres)
hash-chained · door-signed · RFC 6962 tree
budget counters + revocation = PROJECTIONS (replay-checkable)
▼
mandare verify · certify (third-party checkable) · dashboard · killEvery door obeys three rules: fail-closed on spend, log-before-act, and agent input is hostile. Refusals are recorded — the system keeps its no's.
The five demos are the acceptance tests (CI runs all of them)
Shortened. The full README is on GitHub.
Nothing above is checked by us. What we check is on the safety report.
Mandare: common questions
- Is Mandare MCP server safe?
- Yes, by our scan: it is graded A (91/100). Read the Mandare safety report
- How do I install Mandare?
- It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
- Does Mandare need an API key?
- No secret keys are declared. It reads 6 settings from the environment.
- Is Mandare maintained?
- The last commit was 34 days ago (2026-10-01). The latest release is v0.1.0.
- What can I use instead of Mandare?
- Servers from other publishers that do the same job: Basic Memory MCP server, HOL Guard MCP server and Agent-Native Chat MCP server.
- How does Mandare compare with other AI and agents MCP servers?
- safety score 91/100 (higher than 88% of 4,460 AI and agents servers); tools 9 (the typical AI and agents server has 6); tools that change things 11% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.
Alternatives to Mandare
Same job from other publishers: the closest match first, then the best rated.
- Basic MemoryLocal-first knowledge management with bi-directional LLM sync via Markdown files.not reviewedWidely usedB
- HOL GuardLocal-first AI agent security evidence and approval workflows through HOL Guard's stdio MCP server.not reviewedEstablishedA
- Agent-Native ChatMinimal chat-first app with durable threads, actions, and the app-agent loopnot reviewedEstablishedA
- Watch SkillWatch video and live sessions, keep timestamped evidence, and verify an agent's own work.not reviewedEstablishedB
- Actual Budget MCP ServerMCP server exposing Actual Budget accounts, transactions, budgets and reporting to LLM assistants.not reviewedEstablishedB