Connect

8 clients · secrets stay placeholders

JSON (mcpServers)Claude CodeCodexOpenCodeCursorVS CodeGemini CLIGoose

{
  "mcpServers": {
    "safe4": {
      "type": "http",
      "url": "https://api.safe4.ai/mcp/"
    }
  }
}

claude mcp add --transport http safe4 https://api.safe4.ai/mcp/

[mcp_servers.safe4]
url = "https://api.safe4.ai/mcp/"

{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "safe4": {
      "type": "remote",
      "url": "https://api.safe4.ai/mcp/",
      "enabled": true
    }
  }
}

{
  "mcpServers": {
    "safe4": {
      "type": "http",
      "url": "https://api.safe4.ai/mcp/"
    }
  },
  "deeplink": "cursor://anysphere.cursor-deeplink/mcp/install?name=safe4&config=eyJ0eXBlIjoiaHR0cCIsInVybCI6Imh0dHBzOi8vYXBpLnNhZmU0LmFpL21jcC8ifQ%3D%3D"
}

{
  "servers": {
    "safe4": {
      "type": "http",
      "url": "https://api.safe4.ai/mcp/"
    }
  }
}

{
  "mcpServers": {
    "safe4": {
      "httpUrl": "https://api.safe4.ai/mcp/"
    }
  }
}

extensions:
  "safe4":
    enabled: true
    name: "safe4"
    type: streamable_http
    uri: "https://api.safe4.ai/mcp/"
    timeout: 300

Quality 76 / 100good

protocol75 · weight 25

warn
protocol.modernnewest supported version is 2025-11-25; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
n/a
protocol.statelessonly applies to 2026-07-28 servers
pass
protocol.transportstreamable HTTP
n/a
protocol.list_ttlonly applies to 2026-07-28 servers

authorizationn/a · weight 15

n/a
auth.prm, auth.as_metadata, auth.cimdno remote uses OAuth
n/a
auth.secret_in_urlno templated URL

tool hygiene64 · weight 30

pass
tools.descriptionsevery tool has a description
warn
tools.description_length1 tools have descriptions over 1,024 characters, which crowds the context
pass
tools.schemasevery tool has an object input schema
fail
tools.annotationsno tool declares readOnlyHint or destructiveHint, so clients cannot tell safe calls from risky ones
fail
tools.directory_hintsno tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: safe4_price (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); safe4_authorize (readOnlyHint, destructiveHint, idempotentHint, openWorldHint)
pass
tools.token_costabout 663 tokens to load every tool
pass
tools.api_dumptools are not a one-to-one API dump

stability100 · weight 15

pass
stability.changesno tool changes in 30 days
pass
stability.rug_pullno tool changed its meaning under the same name

dependenciesn/a · weight 15

n/a
deps.known_vulns, deps.mcp_sdk_version, deps.resolvableno npm or PyPI package

2 tools, about 663 tokens to load them all · tool set 0ac0e76549cd · checked 2026-10-20 12:13 UTC

Tool changes

No tool definition changes recorded. A server's first observation is its baseline; later probes record what changes.

Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed. How it is computed.

Trust 92 / 100

provenance85

liveness99

freshness85

hygiene100

+repository +dns-namespace +website +reachable +uptime-96% ~updated-54d-ago

Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed. How it is computed.

Endpoints

remote	auth	reachable	uptime 30d	p50	protocol	last ok
`https://api.safe4.ai/mcp/` streamable-http	none	yes	96%	333 ms	2025-11-25	2026-10-20

Tools (2)

safe4_authorize Decide whether a proposed agent payment should proceed. Settled per call in USDC over x402. Called without ``payment`` it returns the price list rather than a decision; call it again with the signed payload to receive one. The task and the two allow-lists are the principal's constraints, not the agent's: they are what the purchase is tested against, so an agent that writes its own ``task`` is grading its own homework. Safe4 records every field it was given in the audit entry and marks the task context as request-supplied, so a substituted constraint is visible afterwards. Args: task: The task the agent was given, as stated by its principal. purchase: What is being bought. purchase_purpose: Why this purchase serves the task. amount: Decimal amount as a string, for example "25.00". currency: Currency of the proposed payment, for example "USDC". counterparty: Who would receive the payment. service_category: Category of the thing being bought. allowed_service_categories: Categories the principal permits. allowed_counterparties: Optional payees the principal permits. When supplied, payment to anyone else is denied. task_id: Optional caller-side task identifier, echoed into the audit. payment: An x402 payment payload for this call. Omit to receive the price list instead of a decision.

safe4_price Price and accepted payment networks for one Safe4 decision. Free to call. Returns the same x402 terms the HTTP endpoint advertises, so an agent can see the cost before committing to a paid call.

Schemas: list_tools.

Similar MCP servers

Official server.json

{
  "name": "ai.safe4/safe4",
  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
  "remotes": [
    {
      "url": "https://api.safe4.ai/mcp/",
      "type": "streamable-http"
    }
  ],
  "version": "1.0.0",
  "repository": {
    "url": "https://github.com/Safe4AI/safe4-mcp",
    "source": "github"
  },
  "websiteUrl": "https://api.safe4.ai/docs",
  "description": "Tests an AI agent's purchase against the task it was given. Paid per call in USDC via x402."
}