MCP.Market

Marchward MCP server

by marchward.ai·ai.marchward/mcp-server·v0.2.4·1 stars
No reviews yet

Runtime authority for AI agents: credential mediation, spend cap, approval gates, audit log.

B77/100grade B
Write a reviewInstall
What users say
No reviews yet
Be the first
Safety scan
B77/100

full report

Adoption
New

1 stars37 downloads/wk

Reviews

Write one

Nobody has reviewed Marchward yet.

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

Marchward tools (7, 1 write)

write = sends, deletes, buys or posts

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

  • marchward_authorize

    Check whether an action is allowed BEFORE the agent takes it. Call this first for any consequential or irreversible action (deploying, committing, publishing, deleting, moving money, calling an external API). Returns ALLOW, BLOCK, ESCALATE, or ALLOW_WITH_CONDITIONS, and writes a tamper-evident audit record. The agent and policy are resolved from your API key, so you usually only pass toolName.

  • marchward_bind_policy

    Attach a governance policy to an agent. After binding, every authorize and execute call from that agent is evaluated against this policy.

  • marchward_check_coverage

    Find governance gaps for an agent by comparing its declared tools against the tools it has actually called. Returns a coverage percentage and the uncovered tools, so ungoverned actions surface before they cause harm. This is the 'Dependabot for governance'.

  • marchward_executewrite action

    Run an action through Marchward's credential-mediated gateway. Marchward evaluates policy, injects the real downstream credential server-side (the agent never holds it), enforces the cost cap and approval gates, then makes the call and records it. Use this for any call to a service whose credentials Marchward manages (GitHub, Stripe, Notion, etc.).

  • marchward_get_decisions

    Review recent governance decisions (the audit trail). Filter by agent, tool name, or outcome (ALLOW/BLOCK/ESCALATE). Use to verify governance is active or to investigate what an agent actually did.

  • marchward_list_agents

    List the agents registered under your account, with their IDs, status, last-seen time, and bound policy. Use to find an agentId or check what is under governance.

  • marchward_register_agent

    Register a new agent with Marchward so it is governed from its first action. Returns the agent record and its Marchward API key — the only credential the agent should hold. Call this when building or deploying a new agent.

Public scan report

scanner v0.1.9 · 2026-09-26 · same rubric, same numbers if you re-run it

no findings
  • Code scan11 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 qualitystatic API keys via environment variables6/15
  • Maintenancelast push 87 days ago12/15
  • Maintainer identityregistry namespace matches repository owner7/10
Overall 77/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Marchward compares

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

Safety score
77/100
higher than 50% of 48,255 servers
Tools
7
the typical server has 7
Tools that change things
14%
typical: 0%. Fewer write tools means less an agent can break
GitHub stars
1
more than 65% of 28,688 servers
Downloads a week
37
more than 28% of 12,191 servers with a package

What its tools let an agent do: 6 read · 1 change

Install Marchward in Claude Code, Cursor or VS Code

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

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

What the publisher says

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

Marchward · runtime authority for AI agents

Marchward

Govern what your AI agents are allowed to do. Marchward is one open layer that sits in front of an agent's tool calls and enforces four controls before any action runs, then writes a tamper-evident record of every decision. Self-hostable, Apache-2.0, framework-agnostic.

  • Credential mediation. The agent holds one Marchward key, never your real GitHub, Stripe, or database credentials. The real secret is injected at execution, and the agent never sees it.
  • Inference spend cap. A hard ceiling on agent spend, so a runaway loop can't drain a budget.
  • Approval gates. Irreversible actions pause for a human instead of running unattended.
  • Tamper-evident audit. Every decision appends to a hash-chained log you can verify offline. Provable, not just logged.

Most tools in this space cover one of these. Marchward brings all four together in one place, open and self-hostable.

Output guardrails check what an agent says (toxicity, PII, topic). Marchward governs what an agent does (spend, delete, act). A check on the agent's output cannot stop an agent that still holds the keys and can make a different call. Marchward governs the action itself.

Built for teams already running agents in production (LangGraph, LangChain, raw SDKs, any MCP server, or one HTTP call from any runtime) who need an agent to be autonomous without being able to drain a budget, take an irreversible action unattended, or act without an audit trail.

Quickstart: govern an agent in 60 seconds (fully local, no account)

marchward-proxy wraps any MCP server as a child process and evaluates every tools/call against your policy before it runs (block, allow, or pause for human approval), entirely on your machine, with your own credentials.

# Write a policy (escalate anything destructive, allow the rest)
cat > policy.json <<'EOF'
{ "rules": [
  { "match": { "toolPattern": "*delete*" }, "decision": "ESCALATE" },
  { "match": { "toolPattern": "*" },        "decision": "ALLOW"   }
]}
EOF

# Put Marchward in front of your agent's MCP server, local mode, no API
npx -p @marchward/proxy marchward-proxy \
  --command "node my-mcp-server.js" \
  --policy-file ./policy.json \
  --local

Every tool call your agent makes now passes through policy first, and lands in a local tamper-evident (hash-chained) audit log you can verify offline. No account, no network call to us.

Prefer the SDK? pip install marchward and wrap calls with marchward.execute(). Point it at your own self-hosted setup, or at the managed plane (below).

What's open vs. what's hosted

The open packages in this repo are a fully functional self-host governor. Some operational features need shared state and run on the hosted plane (free tier, no card):

So: self-host this for execution control, credential mediation from your own local store, a local cost cap, and a local audit log; add the free hosted tier for the managed credential vault (rotation, team sharing), approval workflows, retained audit-as-a-service, and cross-agent enforcement. Same engine underneath. The proxy's --remote mode just points at the plane.

How it works

Shortened. The full README is on GitHub.

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

Marchward: common questions

Is Marchward MCP server safe?
Mostly: it is graded B (77/100). Read the Marchward safety report
How do I install Marchward?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Marchward need an API key?
Yes. The registry entry asks for MARCHWARD_API_KEY.
Is Marchward maintained?
The last commit was 125 days ago (2026-07-01). The latest release is v0.2.4.
What can I use instead of Marchward?
Servers from other publishers that do the same job: SSH — policy-gated remote access MCP server and SSH Manager MCP server.
How does Marchward compare with other MCP servers?
safety score 77/100 (higher than 50% of 48,255 servers); tools 7 (the typical server has 7); tools that change things 14% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.

Alternatives to Marchward

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

  • SSH — policy-gated remote access
    Policy-gated, audited SSH for Linux and Windows hosts: roles, approvals, and an audit log.
    B
  • SSH Manager
    SSH for AI agents: commands, files, backups and health, with approval, a vault and an audit trail
    A