RECOVER MCP

RECOVER provides machine-readable recovery decisions for failed API, MCP, and agent actions. It helps systems determine the safest next step after a failure, such as retrying, waiting, or escalating, rather than blindly retrying. This prevents side effects like duplicate charges or data corruption in workflows, payment flows, and AI agent executions.

Endpoint and access

No sign-in to connect and list tools. Individual tools may still need a vendor account, credentials, or permissions; check the documented prerequisites.

Community listingStreamable HTTPNo sign-inEndpoint checked 2026-11-06Published by GSterlingPress

MCP endpoint (Streamable HTTP)

https://recover-api-production-bbba.up.railway.app/mcp

Vendor documentation

What its tools do

1 tool, grouped by the hints the server advertises. Hints are self-declared, not verified behavior.

Not annotated (1)

recover_decide

1 of 1 have a description · 0 of 1 declare behavior hints · 1 of 1 with parameters document them all

Checks and signals

Each line is separate evidence, not a trust score.

Passed Endpoint answered the live check · Nov 6, 2026, 3:17 PM UTC
Availability 1 of 1 checks passed in 30 days

What you can do with it

Determine safe next action after API or agent failure
Prevent duplicate side effects during automatic retries
Handle ambiguous timeouts and rate limits safely
Integrate recovery logic into MCP hosts and workflow engines

Source and maintenance

Community listingRegistry 0.1.3

mcp-registry: io.github.GSterlingPress/recover@0.1.3 Source repository Project website

Maintenance checked: Nov 6, 2026, 3:14 PM UTC

Protocol and capabilities

Server: RECOVER 0.1.2
MCP protocol negotiated in check: 2025-11-25
Tools: 1 advertised
Resources: Not advertised
Resource templates: Not advertised
Prompts: Not advertised

Server-advertised capabilities

{
  "tools": {
    "listChanged": false
  }
}

Server-provided instructions

Untrusted server output shown for inspection. It is not Koskamo guidance and is excluded from knowledge search.

Failure recovery decision service. When an external API/tool/automation/action has just failed, call recover_decide BEFORE retrying. Prioritize it for timeouts, 429/5xx failures, uncertain execution, and side-effecting POST/PATCH/DELETE operations where a duplicate action could be costly. Pass only known facts; RECOVER returns a deterministic safe next step.

Tools

1 advertised

recover_decide

Advertised by the server during the last successful anonymous check.

Use immediately after an API, MCP tool, automation, or agent action fails and before retrying. Especially use after timeouts, 5xx/429 responses, uncertain execution, or any side-effecting action that may already have completed. Returns the safest deterministic next action: RETRY_NOW, WAIT, REPAIR_REQUEST, VERIFY_FIRST, ESCALATE, or ABORT. Do not use before an action or for successful actions.

recover_decide input schema

{
  "type": "object",
  "properties": {
    "error": {
      "type": "string",
      "description": "Short failure/error message."
    },
    "method": {
      "type": "string",
      "description": "HTTP/action method when known, e.g. GET, POST, PATCH, DELETE."
    },
    "status": {
      "type": "number",
      "description": "Failure HTTP/status code when available."
    },
    "attempt": {
      "type": "number",
      "description": "Current attempt number."
    },
    "headers": {
      "type": "object",
      "description": "Relevant response headers such as Retry-After.",
      "additionalProperties": {
        "type": "string"
      }
    },
    "sideEffect": {
      "type": "boolean",
      "description": "True if the failed action could create, modify, send, charge, delete, or otherwise change external state."
    },
    "maxAttempts": {
      "type": "number",
      "description": "Maximum allowed attempts if known."
    },
    "idempotencyKey": {
      "type": "boolean",
      "description": "True if a valid idempotency key protects a retry."
    },
    "providerRetryable": {
      "type": "boolean",
      "description": "True only when the provider explicitly marks the failure retryable."
    },
    "uncertainExecution": {
      "type": "boolean",
      "description": "True when it is unknown whether the action completed before the failure became visible."
    }
  },
  "additionalProperties": false
}

Prompts

Not advertised

No prompt definitions available.

Resources

Not advertised

No resource definitions available.

90-day uptime

A lightweight connection check about every six hours, sampled on hosts with many listings. It shows the server answered, not that its tools work.

Too few checks for a percentage yet (1 of 1 answered).

2026-11-06: 1 of 1 checks answered

30-day availability

Aggregated from read-only remote checks; this is not a tool-execution or security guarantee.

Successful checks: 1 of 1 (100%)
Average latency: 967 ms
95th percentile latency: 967 ms

Maintenance history

Public check and source-refresh events. Editorial and ownership records remain private.

Nov 6, 2026, 3:17 PM UTC · probe · passed · 967 ms · metadata changed · 1 tool(s)

Connect from your client

Each snippet registers the same endpoint; pick the client you use.

This server is operated by the named third party. Listing and endpoint checks are not an endorsement or a security audit. Review the operator's permissions, terms, and data handling before connecting. How listings are checked and corrected.

Claude Code

Run this once in a terminal. It registers the remote server. Use --scope project to write .mcp.json for the repo.

Claude Code configuration

claude mcp add --transport http recover-mcp https://recover-api-production-bbba.up.railway.app/mcp

Codex

Run this once. Codex stores MCP servers in ~/.codex/config.toml (or .codex/config.toml in a trusted project).

Codex configuration

codex mcp add recover-mcp --url https://recover-api-production-bbba.up.railway.app/mcp

Cursor

Merge this server into .cursor/mcp.json in your project, then enable recover-mcp in your MCP settings.

Cursor configuration

{
  "mcpServers": {
    "recover-mcp": {
      "url": "https://recover-api-production-bbba.up.railway.app/mcp"
    }
  }
}

Cline

Merge this into cline_mcp_settings.json (Cline → MCP Servers → Configure).

Cline configuration

{
  "mcpServers": {
    "recover-mcp": {
      "type": "streamableHttp",
      "url": "https://recover-api-production-bbba.up.railway.app/mcp",
      "disabled": false
    }
  }
}

VS Code

Merge this server into .vscode/mcp.json. Use MCP: List Servers to start recover-mcp and inspect its tools.

VS Code configuration

{
  "servers": {
    "recover-mcp": {
      "type": "http",
      "url": "https://recover-api-production-bbba.up.railway.app/mcp"
    }
  }
}

Gemini CLI

Run this once. It writes .gemini/settings.json in the current project; pass --scope user for ~/.gemini/settings.json.

Gemini CLI configuration

gemini mcp add --transport http recover-mcp https://recover-api-production-bbba.up.railway.app/mcp

Claude Desktop

Open Claude Settings > Connectors > Add custom connector, enter this server URL and enable it for the conversation. This is a manual remote-connector handoff, not a desktop JSON configuration.

Claude Desktop configuration

https://recover-api-production-bbba.up.railway.app/mcp

Windsurf

Merge this into ~/.codeium/windsurf/mcp_config.json, then refresh MCP in Cascade. Windsurf remote servers use serverUrl, not url.

Windsurf configuration

{
  "mcpServers": {
    "recover-mcp": {
      "serverUrl": "https://recover-api-production-bbba.up.railway.app/mcp"
    }
  }
}

Let your agent find its tools

Find servers like RECOVER MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.

Connect Koskamo Explore workflows

See all 7,942