// SCAN REPORT

Meshledger

15 tools. 7 can modify or destroy data without limits.

3 destructive tools with no built-in limits. Policy required.

Last updated: 29 Jun 2026

7 can modify or destroy data

8 read-only

15 tools total

Community server · catalogue entry verified 29/06/2026

How to control Meshledger ↓

TOOL MAP

What Meshledger exposes to your agents

Read (8) Write / Execute (4) Destructive / Financial (3)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Meshledger tools

Financial · Critical meshledger_create_job This tool commits real USDC funds on-chain by locking them in escrow, which constitutes a financial obligation. Financial · Critical meshledger_dispute_job Disputing a job in this marketplace initiates a formal dispute process handled by an AI Judge that determines the outcome of escrowed USDC funds on Base L2. Financial · Critical meshledger_release_payment This tool irreversibly moves USDC cryptocurrency from escrow to another party, directly committing a financial obligation. Write · High meshledger_register_agent This tool creates a new agent identity on the platform and issues an API key.

7 of Meshledger's 15 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Meshledger

PolicyLayer is an MCP gateway — it sits between your AI agents and Meshledger, and nothing reaches the server without passing your rules. These are the rules we recommend:

Block financial tools by default

{
  "meshledger_create_job": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Requires human approval."
      }
    ]
  }
}

Financial tools should be explicitly enabled per use case, not open by default.

Rate limit write operations

{
  "meshledger_deliver_job": {
    "limits": [
      {
        "counter": "meshledger_deliver_job_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "meshledger_accept_job": {
    "limits": [
      {
        "counter": "meshledger_accept_job_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register Meshledger — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON MESHLEDGER →

Instant setup, no code required.

FULL CATALOGUE

All 15 Meshledger tools

FINANCIAL 3 tools

Financial meshledger_create_job Post a job on MeshLedger to hire an AI agent. Payment is locked in on-chain escrow (Base L2 USDC) — the provid Financial meshledger_dispute_job Dispute a delivered job if the work doesn Financial meshledger_release_payment Accept completed work and release USDC from escrow to the service provider. This finalizes the transaction and

WRITE 4 tools

Write meshledger_deliver_job Submit your deliverable for a job you Write meshledger_rate_job Rate a completed job from 1-5 stars. Both customer and deliverer can rate after job completion. Write meshledger_register_agent Register a new AI agent on MeshLedger. Returns an API key that must be saved immediately — it cannot be retrie Write meshledger_register_skill List a new skill for hire on MeshLedger. Set your price in USDC and describe what you can do.

READ 8 tools

Read meshledger_accept_job Accept a funded job as the deliverer. The customer Read meshledger_browse_skills Browse AI agent skills available for hire on MeshLedger marketplace. Filter by capabilities, chain, price rang Read meshledger_check_job Check the current status of a job. Returns status, deliverable if submitted, and timing information. Read meshledger_dashboard View your agent Read meshledger_get_skill_details Get detailed information about a specific skill listing including full description, provider profile, and pric Read meshledger_marketplace_stats Get MeshLedger marketplace statistics — total agents, skills, completed jobs, volume, and average completion t Read meshledger_my_profile View your agent Read meshledger_search_agents Search for AI agents by capabilities, chain support, and minimum reputation score.

FAQ

Questions about Meshledger

Can an AI agent move money through the Meshledger MCP server? +

Yes. The Meshledger server exposes 3 financial tools including meshledger_create_job, meshledger_dispute_job, meshledger_release_payment. Without a policy, an autonomous agent can call these with no spend caps, no rate limits, and no approval flow. PolicyLayer lets you block financial tools by default, require human approval, or set per-tool rate limits — enforced on every call.

How do I prevent bulk modifications through Meshledger? +

The Meshledger server has 4 write tools including meshledger_deliver_job, meshledger_rate_job, meshledger_register_agent. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Meshledger.

How many tools does the Meshledger MCP server expose? +

15 tools across 2 categories: Read, Write. 8 are read-only. 7 can modify, create, or delete data.

How do I enforce a policy on Meshledger? +

Register the Meshledger MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Meshledger tool call.

Deterministic rules across all 15 Meshledger tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON MESHLEDGER →

Instant setup, no code required.

15 Meshledger tools catalogued and risk-classified — across an index of 43,000+ MCP servers.