Hesperan MCP Server

by hesperan Your server? Claim it

answering

Hesperan is answering right now. Last checked 10 min ago. 27 installs a week from npm. It exposes 3 tools.

Calibrated decisions for agents: choice, yes/no and score questions answered with probabilities.

Installs per day peak 127 · avg 6

a month agotoday

Uptime history 18 days of history

18 days agonow

100.0%

Uptime 24h

91 of 91 checks

Tools

read from the server

124 ms

Response time

average over 24h

Installs / week

npm and PyPI

Nothing serious here today

Today is the operative word: we check Hesperan every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 10 min ago.

Claude Code Claude Desktop Codex Cursor VS Code

run in your terminal

claude mcp add mcp --transport http https://api.hesperan.com/mcp

~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "mcp": {
      "url": "https://api.hesperan.com/mcp"
    }
  }
}

~/.codex/config.toml

[mcp_servers.mcp]
url = "https://api.hesperan.com/mcp"

.cursor/mcp.json

{
  "mcpServers": {
    "mcp": {
      "url": "https://api.hesperan.com/mcp"
    }
  }
}

.vscode/mcp.json

{
  "mcpServers": {
    "mcp": {
      "url": "https://api.hesperan.com/mcp"
    }
  }
}

This one needs environment variables set before it will start: HESPERAN_API_KEY (Hesperan API key (hsp_...) from https://hesperan.com/console/keys), HESPERAN_BASE_URL (API base URL). The author declared them in the registry entry; get the values from the project itself.

Available tools 3

Read directly from the server with tools/list, grouped by what they act on. If a tool disappears, we record the date.

decide

decide

Ask Hesperan 1 one or more typed questions about a state and get a probability for every possible answer. Types: choice (pick one of named options), noul (probability that a statement is true), score (level on an ordinal scale). Use for decisions with known options: routing, triage, policy or risk checks, "should I proceed?". Not for writing text, summaries or knowledge questions. Ask all questions about the same state in one call: billing is by input tokens (the state once plus each question once), from the user's monthly allowance and then their prepaid balance; failed calls are free.

decide_with_profile

Run one of the user's decision profiles on a state. A profile is one question calibrated on the user's own labelled cases with a target precision; the answer is a decision, its calibrated confidence and an action: "auto" (confidence reaches the profile's threshold — act on it) or "review" (hand it to a person). Profiles are created in the Hesperan console; ask the user for the profile slug. Keep the returned decision_id to report the correct answer later with report_outcome. Billed by input tokens like decide; pass an idempotency_key to make retries safe (a repeat with the same key returns the first decision without charging again).

report

report_outcome

Record the correct answer for an earlier decide_with_profile decision, once it is known (e.g. the team that finally handled the ticket). This tracks the live precision of the profile in the console. actual must be one of the profile's option keys. Free of charge.

Endpoints

URL	Transport	State	Latency	Checked
https://api.hesperan.com/mcp	streamable-http	answering	72 ms	10 min ago

Alternatives to Hesperan

same job, measured the same way

Jev-Style

by lawrence3699

Local 2B and 0.8B decision models: calibrated yes/no, choice and score answers for your agent.

518 installs/wk local only

Jev Decision MCP

by amidabuddha

Typed Jev decisions in one batched tool: choice, score, and yes/no probabilities.

62 installs/wk local only

OpenJEV

by markylaredo

Typed AI judgments for agents: choice, score, and yes/no probabilities instead of prose.

394 installs/wk local only

Ask Jev

by pollinations

Evaluate state with typed choice, score, and probability questions.

answering

Hunch

by hunchsheet

Calibrated judgments for text: yes/no probabilities, picks from your options, or scores.

8 tools answering

ember

by shapeandshare

Calibrated advice for coding agents: typed questions in, probabilities out. Apple Silicon.

3 381 installs/wk local only

Jev MCP Server

by wangkuangkuang

MCP server for Jev (TypeSafe System One): typed decisions with calibrated probabilities.

328 installs/wk local only

Smoke Signal

by smoke-signal-app

Phone notifications and phone-answered questions for AI agents: notify and decision-request tools.

local only

Hesperan — questions

Answers built from our own checks of this server.

What can Hesperan do?

It exposes 3 tools, read directly from the server on our last check. Among them: decide, decide_with_profile, report_outcome. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README. How MCP servers expose tools in the first place →

Is Hesperan working right now?

We send a real MCP handshake every 15 minutes. Over the last 24 hours 91 of 91 checks got a reply (100.0%), average response time 124 ms. The bar chart above shows every period we have measured.

How do I connect Hesperan?

Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.

Does Hesperan need an API key?

No. Hesperan completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 3 of them are readable on this page. This is what we observed, not what the docs claim.

How fast is Hesperan?

It answers our handshake in 124 ms on average, which is faster than 77% of all working MCP servers we measure. That puts it in the quick quarter of the ecosystem. The comparison comes from our own checks across the whole registry, every 15 minutes.

How many people use Hesperan?

The npm package hesperan-mcp was installed 27 times in the last week. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.