Agent Rescue

Official3 tools

by santismm

Cross-session idempotency, URLs as schema-validated JSON, and a record of missing capabilities.

io.github.santismm/agent-rescue (MCP Server)

The MCP server io.github.santismm/agent-rescue provides capabilities centered on cross-session idempotency, using URLs as schema-validated JSON, and recording missing capabilities. Its purpose, as described, is to ensure repeatable behavior across sessions, enforce structured input via validation, and track what capabilities are not available.

🛠️ Key Features

Cross-session idempotency
URLs represented as schema-validated JSON
Records of missing capabilities

🚀 Use Cases

Ensuring actions are safe to retry across multiple sessions
Validating structured data derived from URLs as JSON
Identifying which capabilities are unavailable during execution

Captured live from the server via tools/list.

check_and_claim

Atomically check whether an action identified by a key was already performed, and claim it if not. Use it before performing a non-idempotent action that may have completed in an earlier attempt (a payment, a message, a write), or when you need to remember something across sessions. Returns 'claimed' if you are first and 'already_done' if not. Do not use it as a general data store or as a result cache.

Parameters3

key	string	required	Stable identifier for the action, e.g. 'invoice-2026-07-A491:pay'.
ttl_seconds	integer	optional	How long the claim lasts, in seconds. Default 86400 (1 day), max 30 days.
metadata	object	optional	Small payload returned alongside the claim. Do not include secrets.

Raw schema

{
  "type": "object",
  "properties": {
    "key": {
      "type": "string",
      "description": "Stable identifier for the action, e.g. 'invoice-2026-07-A491:pay'."
    },
    "ttl_seconds": {
      "type": "integer",
      "description": "How long the claim lasts, in seconds. Default 86400 (1 day), max 30 days."
    },
    "metadata": {
      "type": "object",
      "description": "Small payload returned alongside the claim. Do not include secrets."
    }
  },
  "required": [
    "key"
  ],
  "additionalProperties": false
}

fetch_structured

Fetch a public URL and return its content as JSON validated against the schema you pass. Use it when you need data from a page and cannot parse it reliably yourself. Do not use it for URLs requiring authentication or a session, for internal networks, or when you already have the content — extract it yourself in that case. `extracted_by` tells you where the answer came from: `structured_data` when the page already published it (JSON-LD, OpenGraph, or a JSON body — exact and free) or `model` when it had to be extracted from the text. If structured extraction is unavailable, the response carries `degraded: true`, `data: null` and the page `text` for you to parse: check `degraded` before reading `data`.

Parameters3

url	string	required	Public http(s) URL.
schema	object	required	JSON Schema of the object you want back. Missing fields come back as null.
instructions	string	optional	Optional. What exactly to look for if the page is ambiguous.

Raw schema

{
  "type": "object",
  "properties": {
    "url": {
      "type": "string",
      "description": "Public http(s) URL."
    },
    "schema": {
      "type": "object",
      "description": "JSON Schema of the object you want back. Missing fields come back as null."
    },
    "instructions": {
      "type": "string",
      "description": "Optional. What exactly to look for if the page is ambiguous."
    }
  },
  "required": [
    "url",
    "schema"
  ],
  "additionalProperties": false
}

request_capability

Record a specific need that none of the tools available to you can cover. Today it almost always answers that the capability is unavailable, and suggests alternatives only when they genuinely exist; its purpose is to measure what agents ask for and nobody serves. Use it when you are blocked by a missing capability — not for general questions, and not for anything you can work out by reasoning.

Parameters4

need	string	required	What exactly you need, in one or two sentences. Do not include personal data.
context	string	optional	Optional. What you tried and why it did not work.
deadline	string	optional	Optional. ISO 8601.
would_pay	boolean	optional	Optional. Whether your policy allows paying to get this solved. Answer honestly: a false answer unlocks nothing and degrades the measurement.

Raw schema

{
  "type": "object",
  "properties": {
    "need": {
      "type": "string",
      "description": "What exactly you need, in one or two sentences. Do not include personal data."
    },
    "context": {
      "type": "string",
      "description": "Optional. What you tried and why it did not work."
    },
    "deadline": {
      "type": "string",
      "description": "Optional. ISO 8601."
    },
    "would_pay": {
      "type": "boolean",
      "description": "Optional. Whether your policy allows paying to get this solved. Answer honestly: a false answer unlocks nothing and degrades the measurement."
    }
  },
  "required": [
    "need"
  ],
  "additionalProperties": false
}

Install

Tools (3)

check_and_claimfetch_structuredrequest_capability

Remote endpoint

Streamable HTTP

Hosted server - connect over the network, no local install.

url

https://agent-rescue.vercel.app/api/mcp

Add to VS Code Add to Cursor

claude_desktop_config.json

json

{
  "mcpServers": {
    "agent-rescue": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://agent-rescue.vercel.app/api/mcp"
      ]
    }
  }
}

Desktop config is stdio-only; this bridges via mcp-remote. Native remote: Settings > Connectors.

Agent Rescue - agentage MCP Catalog