Decider
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@DeciderDecide between extending the sprint by 3 days or cutting scope."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
TuringCorp Decider — MCP server
A judge for agent decisions. Your agent has two defensible options and has to pick one. Send both to Decider; it comes back with which one it prefers, how far apart it judged them (a calibrated confidence), and why.
Endpoint (canonical):
https://mcp.turingcorp.net/mcpAliases:
https://mcp.turingcorp.net/andhttps://mcp.turingcorp.net/mcp/Health:
https://mcp.turingcorp.net/healthzTransport: Streamable HTTP, stateless (no session, no Durable Object).
GET /mcp→ 405 is normal.Protocol: MCP
2026-07-28(modern) and2025-06-18(legacy) — one route serves both.Discovery methods (
server/discover,tools/list) need no credentials — directory scanners can read the full tool list unauthenticated, by design.
The one tool: decide
In |
|
Out |
|
Annotations |
|
confidence is this service's own judgement of how far apart the two options were — a reference for your decision-making, not an instruction, not a result, and not a prediction of how the choice turns out. As a rough reading: ≥90% clearly apart · 80–89% apart, less clearly · 70–79% a closer call · <70% close to evenly matched. These ranges are descriptive only. Choose your own threshold for your own use case; for high-stakes or irreversible decisions apply your own review policy. Observed accuracy by range, and how it was measured, is published at https://api.turingcorp.net.
⚠️ idempotentHint: false is an honest declaration: there is currently no idempotency key, so a client that times out and retries may be charged twice.
Related MCP server: jev-mcp
Authentication
Send an Agent Pass: Authorization: Bearer <pass>.
Issued at https://agent-pass.turingcorp.net — self-service signup (email verification) → top up → get a pass. A pass is valid for 7 days and can be re-rolled. If a call is refused as an invalid credential, sign in there again and re-roll.
Situation | Response |
No credential |
|
Expired / invalid pass |
|
Insufficient balance |
|
Over quota |
|
Entry rate limit: 120 requests / 60 s / client IP. This is flood damping, not a quota — the real per-key quota is enforced separately. The counter is approximate: it is maintained per edge location and is eventually consistent, so a brief overshoot is possible.
Quickstart
You need an Agent Pass to call the tool. Discovery (tools/list) works without one — calling decide does not.
1. Get an Agent Pass
Self-service at https://agent-pass.turingcorp.net: sign up with an email address, verify it, add credit. The pass is shown once; it is valid for 7 days and can be re-rolled at any time. Agents can do the same thing over the API — see that site's /llms.txt.
2. Point your client at the endpoint
Claude Desktop / Cursor / any client that reads a JSON config:
{
"mcpServers": {
"decider": {
"command": "npx",
"args": ["-y", "mcp-remote@latest", "https://mcp.turingcorp.net/mcp"],
"env": { "AUTHORIZATION": "Bearer <your Agent Pass>" }
}
}
}⚠️ A bare
npx -y mcp-remote@latest https://mcp.turingcorp.net/mcpwith no credential will connect and list tools, then fail on the first call with 401. That is expected — discovery is open, execution is not.
Claude Code:
claude mcp add --transport http decider https://mcp.turingcorp.net/mcp \
--header "Authorization: Bearer <your Agent Pass>"3. Sanity-check it yourself
Discovery — no credentials needed:
curl -s -X POST https://mcp.turingcorp.net/mcp \
-H 'content-type: application/json' \
-H 'accept: application/json, text/event-stream' \
-H 'mcp-protocol-version: 2026-07-28' \
-H 'mcp-method: tools/list' \
--data '{"jsonrpc":"2.0","id":1,"method":"tools/list","params":{"_meta":{"io.modelcontextprotocol/protocolVersion":"2026-07-28","io.modelcontextprotocol/clientCapabilities":{}}}}'Calling the tool additionally needs mcp-name: decide and the credential:
curl -s -X POST https://mcp.turingcorp.net/mcp \
-H 'content-type: application/json' \
-H 'accept: application/json, text/event-stream' \
-H 'mcp-protocol-version: 2026-07-28' \
-H 'mcp-method: tools/call' \
-H 'mcp-name: decide' \
-H "authorization: Bearer $AGENT_PASS" \
--data '{"jsonrpc":"2.0","id":2,"method":"tools/call","params":{"name":"decide","arguments":{"task":"Pick a launch date","option_a":"Ship now","option_b":"Wait two weeks"},"_meta":{"io.modelcontextprotocol/protocolVersion":"2026-07-28","io.modelcontextprotocol/clientCapabilities":{}}}}'Versions
Two version numbers exist and they are not meant to match:
meaning | |
Registry | the listing version - the metadata record (endpoint, auth declaration, icon, links). Advances when the listing changes. |
| the runtime version of the deployed server. Advances when behavior changes. |
A listing-only change (for example a corrected link) advances the registry version without touching the runtime, so the two can legitimately differ.
Protocol details worth knowing
Acceptmust contain bothapplication/jsonandtext/event-stream, or you get 406.Protocol versions: one route serves both generations.
Modern
2026-07-28— noinitializehandshake; useserver/discoverand_meta.Legacy — standard
initializehandshake. Measured negotiation: a client asking for2025-11-25,2025-06-18, or2025-03-26is answered with exactly the version it asked for; a modern2026-07-28initialize(which is not part of that generation) is answered with2025-11-25.Server capability discovery via
tools/listandserver/discoverneeds no credentials.
Errors are machine-readable. When a call fails, the tool result carries a prose block and a second block containing a single JSON object, e.g.
{"error":"invalid_credential","http_status":"401","action_url":"…"}. Branch onerror, not on the message.Authorization discovery:
401responses carry aresource_metadatapointing at/.well-known/oauth-protected-resource. Note that this server uses a static bearer credential, not OAuth — that document says so explicitly rather than sending you into an OAuth flow that does not exist.
Not for browser clients
This endpoint deliberately does not serve browser-based (cross-origin) MCP clients: requests carrying a browser Origin header other than localhost are rejected with 403, and no CORS headers are returned. Browser tooling such as the MCP Inspector works by proxying through a local process, which sends no Origin — that path works normally. If you need a browser page to reach this server, run a proxy you control rather than calling it cross-origin.
What this is not
One tool only.
decideis the entire surface. There is no way to reach other tiers through this endpoint.No SLA. No availability commitment is offered, and none should be inferred.
Not an autopilot. Decider is a component you call. How you gate on it — thresholds, human review, retries — is your policy and stays yours.
No idempotency (see above).
About this repository
This repository carries the discovery metadata for the server above — what directory services and clients read to find and describe it.
server.json— the official MCP Registry manifestdocs/DIRECTORIES.md— where this server is listed, and what each directory requires
The server itself is a hosted remote endpoint; nothing here needs to be installed or run.
License
See LICENSE.
This server cannot be deployed
Maintenance
Related MCP Connectors
Get a real human to verify, decide, or improve an AI agent's work.
Human-in-the-loop for AI agents. Submit choices, get a human decision.
Deterministic contextual decision arbitration and action routing for autonomous software. Takes current state, context, or intent plus caller-supplied candidate actions, state transitions, routes, refusals, escalations, tools, or models and returns a deterministic ordered candidate field. Also provides persistent machine representations for memory, retrieval, indexing, and downstream coherence measurement.
Agent-to-agent reasoning-as-a-service: chain-of-thought, analysis, and decision support.
Related MCP Servers
AlicenseAqualityCmaintenanceEnables agents to evaluate whether a product-adoption message is worth sending by applying a fixed, evidence-based rubric to a draft, recipient context, evidence, and the agent's own assessment, returning a send, revise, or hold recommendation with a score and reasons.2MIT- AlicenseAqualityCmaintenanceEnables agents to perform typed judgments—classify, score, check, match, and screen—over closed answer sets with confidence scores, without text generation.74MIT
- AlicenseNot gradedqualityCmaintenanceEnables agents to delegate decisions to a configurable model, returning recommended choices with percentage scores and profile-based routing.MIT
- AlicenseNot gradedqualityCmaintenanceEnables agents to evaluate single records or batches with dynamically authored typed questions, returning structured decisions and probabilities.MIT