Index / MCP servers / Hunchful

Hunchful MCP server

Hunchful is a remote MCP server that gives an AI agent 7 tools, among them add_hunch, apply_refinement, find_complementary_thinkers. It answers at https://hunchful.io/mcp over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 6 of 6 times since 11 September 2026; the last check, on 24 October 2026, succeeded.

Status
Answering
Tools
7
Official
yes, served from hunchful.io
Reliability
6 of 6 checks
Response time
261 ms
Transport
streamable HTTP
Last checked
24 October 2026

Read and grow a person's falsifiable, consent-based model of how they work with AI (CMP).

Description as the publisher wrote it.

The 7 tools Hunchful offers

ToolWhat it does
add_hunchRecord a NEW hunch the person just confirmed in conversation — a custom axis with their answer, added directly to their model (visible, revisable, removable by them). OWNER-LEVEL trust required: OAuth as the owner, or the editToken. Only re
Inputs: modelId, editToken, name, poleA, poleB, pole
apply_refinementApply a refinement directly as one logged revision (append evidence pointers, nudge confidence). Authorized by OAuth (own model) or an editToken. Prefer propose_refinement unless the owner asked for direct writes.
Inputs: modelId, editToken, items
find_complementary_thinkersWhich famous thinkers would COMPLETE this person — opposite poles on the axes where opposites unstick each other (not similarity). Open read; great for curiosity and for explaining what a complementary collaborator looks like. Share the pag
Inputs: modelId
find_matchesLook for complementary PEOPLE for the connected person (rule: agents propose, humans accept — this creates pending proposals the human decides on in their Hunchful hub; identities are never revealed here). Requires OAuth as the owner or the
Inputs: modelId, editToken, direction
propose_refinementPropose a refinement (provenance pointers only). It lands in the owner's confirm queue — nothing changes until they accept. Authorized by OAuth (own model) or a contributionToken.
Inputs: modelId, contributionToken, items
read_modelRead a Hunchful collaboration model: its hunches (axis, pole, confidence), the axis ids you can refine, and how you're connected. Start here. With OAuth, omit modelId to read the connected person's own model.
Inputs: modelId
suggest_questionSuggest a NEW question/axis for the person — a dimension their model doesn't capture (situational axes welcome: name it 'When <situation>'). It lands in their Hunchful inbox and, by default, emails them; nothing is added until they answer.
Inputs: modelId, contributionToken, name, poleA, poleB, question

Add Hunchful to your AI client

Every block below points at https://hunchful.io/mcp. Pick your client and copy.

Claude Code: one command in your terminal
claude mcp add --transport http hunchful https://hunchful.io/mcp
Claude Desktop: claude_desktop_config.json
{
  "mcpServers": {
    "hunchful": {
      "command": "npx",
      "args": ["-y", "mcp-remote", "https://hunchful.io/mcp"]
    }
  }
}
Cursor: ~/.cursor/mcp.json, or .cursor/mcp.json in a project
{
  "mcpServers": {
    "hunchful": {
      "url": "https://hunchful.io/mcp"
    }
  }
}
VS Code and GitHub Copilot: .vscode/mcp.json
{
  "servers": {
    "hunchful": {
      "type": "http",
      "url": "https://hunchful.io/mcp"
    }
  }
}
Zed: Zed settings.json
{
  "context_servers": {
    "hunchful": {
      "url": "https://hunchful.io/mcp"
    }
  }
}
Windsurf: ~/.codeium/mcp_config.json
{
  "mcpServers": {
    "hunchful": {
      "serverUrl": "https://hunchful.io/mcp"
    }
  }
}
JetBrains AI Assistant: Settings, Tools, AI Assistant, MCP, New MCP Server, as JSON
{
  "mcpServers": {
    "hunchful": {
      "url": "https://hunchful.io/mcp"
    }
  }
}
Continue: .continue/mcpServers/neuronto.yaml
name: Hunchful
version: 0.0.1
schema: v1
mcpServers:
  - name: Hunchful
    type: streamable-http
    url: https://hunchful.io/mcp
Gemini CLI: ~/.gemini/settings.json
{
  "mcpServers": {
    "hunchful": {
      "httpUrl": "https://hunchful.io/mcp"
    }
  }
}
Codex CLI: MCP server config
{
  "mcpServers": {
    "hunchful": {
      "type": "http",
      "url": "https://hunchful.io/mcp"
    }
  }
}
Warp: MCP servers, + Add, paste JSON
{
  "mcpServers": {
    "hunchful": {
      "url": "https://hunchful.io/mcp"
    }
  }
}
Goose: a one-click extension link
goose://extension?url=https%3A%2F%2Fhunchful.io%2Fmcp&type=streamable_http&id=hunchful&name=Hunchful

Is Hunchful up right now?

It answered our last check on 24 October 2026 in 261 ms. Over 6 checks since 11 September 2026 it answered 6. Status here comes from Neuronto's own probes, not from the publisher.

MCP servers similar to Hunchful

Questions about Hunchful

Is there an official Hunchful MCP server?

Yes. It is published by hunchful.io and served from hunchful.io, the vendor's own domain: https://hunchful.io/mcp.

How many tools does Hunchful have?

7, as returned by the server's own tools/list on 22 September 2026: add_hunch, apply_refinement, find_complementary_thinkers, find_matches, propose_refinement, read_model, suggest_question.

Is Hunchful down?

It answered our last check on 24 October 2026 in 261 ms. Over 6 checks since 11 September 2026 it answered 6.

How do I add Hunchful to Cursor?

Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://hunchful.io/mcp. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.

Does Hunchful need an API key?

It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.

Where this comes from

Publisher: io.hunchful. Endpoint host: hunchful.io. ARD identifier: urn:air:io.hunchful:mcp:hunchful. First indexed 10 September 2026. The tools are exactly what the server returned; nothing on this page is inferred from its name. Ranking in Neuronto search is never for sale.

Is this your server? Get a message the day it stops answering or its tools change: monitoring, 14 days free. Or claim the domain to manage how it is listed.