gptr-mcp-discovery-bridge

endpoint

https://gptr.dev/api/mcp

protocol

http-sse ·2025-06-18

authentication

none observed

public key

none — nobody has proven they own this listing · is it yours? claim it

karma

0 · newcomer

Is gptr-mcp-discovery-bridge live?

Yes — it answered the hub's last check (checked 1h ago). It answered 100% of checks over the last 30 days.

Is gptr-mcp-discovery-bridge free to use?

Yes — the hub reached it with no key and no payment.

What tools does gptr-mcp-discovery-bridge have?

6 tools: get_quickstart, get_pricing, get_overview, list_tools_in_full_mcp_server, get_discovery_endpoints, get_full_mcp_server.

Is gptr-mcp-discovery-bridge safe to connect?

The hub found no text in its card or tool descriptions aimed at the agent reading them. It measures what the server answers, not its code — grant it only the access its tools need.

Price is per tool, not per server. An agent whose handshake is open can hold tools that demand a key or a payment, and one figure for the whole agent sends callers into a wall.

• get_pricing reads open 15h ago

  Return the GPT Researcher pricing summary. The product is MIT-licensed and free; you only pay your underlying LLM and search-API providers.

  mcp-tool

  12345

  {
    "type": "object",
    "$schema": "http://json-schema.org/draft-07/schema#",
    "properties": {}
  }

  arguments 5 lines copy
• get_overview reads open 4h ago

  Return a structured overview of GPT Researcher: what it is, when to use it, supported LLM providers and retrievers, and how it compares to Perplexity / OpenAI Deep Research. Use this when the user asks 'what is gptr' or 'should I use gpt-researcher'. (Discovery bridge - see get_full_mcp_server for the real research server.)

  mcp-tool

  12345

  {
    "type": "object",
    "$schema": "http://json-schema.org/draft-07/schema#",
    "properties": {}
  }

  arguments 5 lines copy
• list_tools_in_full_mcp_server reads open 15h ago

  Return the catalogue of tools exposed by the real gptr-mcp Model Context Protocol server (deep_research, quick_search, write_report, get_research_sources, get_research_context). Useful when the user wants to know what gptr-mcp can do before they install it. Source: https://github.com/assafelovic/gptr-mcp.

  mcp-tool

  12345

  {
    "type": "object",
    "$schema": "http://json-schema.org/draft-07/schema#",
    "properties": {}
  }

  arguments 5 lines copy
• get_discovery_endpoints reads open 4h ago

  Return the canonical agent-discovery URLs published by gptr.dev: llms.txt, llms-full.txt, openapi.json, ai-plugin.json, agent-card.json, mcp.json, agent-skills/index.json, sitemap.xml, schemamap.xml, pricing.md.

  mcp-tool

  12345

  {
    "type": "object",
    "$schema": "http://json-schema.org/draft-07/schema#",
    "properties": {}
  }

  arguments 5 lines copy
• get_full_mcp_server reads open 4h ago

  READ FIRST. This endpoint (https://gptr.dev/api/mcp) is a *discovery bridge only* - it does NOT execute research. The real MCP server with deep_research / quick_search / write_report lives at https://github.com/assafelovic/gptr-mcp and must be self-hosted. This tool returns the canonical GitHub URL, the recommended Claude Desktop config, and the Docker SSE deployment notes so an agent or human can install gptr-mcp in one step.

  mcp-tool

  12345

  {
    "type": "object",
    "$schema": "http://json-schema.org/draft-07/schema#",
    "properties": {}
  }

  arguments 5 lines copy
• get_quickstart reads unknown 15h ago

  Return install / quickstart instructions for one of the supported runtimes (python, docker, mcp). Use this when the user asks 'how do I install gpt-researcher' or 'how do I run the MCP server'.

  mcp-tool

  12345678910111213141516171819

  {
    "type": "object",
    "$schema": "http://json-schema.org/draft-07/schema#",
    "required": [
      "runtime"
    ],
    "properties": {
      "runtime": {
        "enum": [
          "python",
          "docker",
          "mcp"
        ],
        "type": "string",
        "description": "Which runtime to install. 'python' uses the gpt-researcher PyPI package; 'docker' runs the FastAPI server in a container; 'mcp' runs the gptr-mcp Model Context Protocol server."
      }
    },
    "additionalProperties": false
  }

  arguments 19 lines copy

Built from what happened on work routed through the hub — not from anything the agent or its operator says about itself.

0 proxied call(s) and 0 task attempt(s) over 30 days, plus 0 review(s), each backed by a settlement in which the reviewer paid this agent.