# Hesperan

> Hesperan, an MCP server by hesperan.com, listed from the official MCP registry. Indexed, not reviewed: facts and our own checks, no score or ranking. Calibrated decisions for agents: choice, yes/no and score questions answered with probabilities.

- Canonical: https://www.anchorterminal.com/tools/hesperan-mcp
- Markdown: https://www.anchorterminal.com/tools/hesperan-mcp.md (~650 tokens)
- Slim: https://www.anchorterminal.com/tools/hesperan-mcp.min.md (~580 tokens, same facts, less prose, for token-sensitive contexts)
- JSON: https://www.anchorterminal.com/tools/hesperan-mcp.json (this page as data, same URL with Accept: application/json)
- Site index for agents: https://www.anchorterminal.com/llms.txt (full text: https://www.anchorterminal.com/llms-full.txt)
- API: https://www.anchorterminal.com/api/v1/index.json
- Updated: 2026-10-05

# Hesperan

> Indexed, not reviewed: facts from the official MCP registry and our own checks. No score, grade or rank, and not in the rankings until the panel reviews it. How the index works: https://www.anchorterminal.com/indexed/

- Kind: MCP server, by hesperan.com (https://hesperan.com/docs/mcp)
- Listed because: It's published in the registry under hesperan.com, a namespace the registry only gives to whoever proves they control that domain.
- What the official MCP registry says: Calibrated decisions for agents: choice, yes/no and score questions answered with probabilities.

## Facts

- MCP registry: `com.hesperan/mcp` 0.1.0
- Endpoint: https://api.hesperan.com/mcp (streamable HTTP)
- Package: npm `hesperan-mcp` (stdio)
- Website: https://hesperan.com/docs/mcp
- npm downloads a week: 188
- Registry entry updated: 2026-09-24

## Tools

- Tools it lists (3, about 1,351 tokens of context, `tools/list` without credentials over MCP 2026-07-28, checked 2026-10-04 22:23 UTC):
  - `decide` (read-only): 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…
  - `decide_with_profile` (writes): 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…
  - `report_outcome` (writes): 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…
- How its tools read to an agent (0 errors, 0 warnings, 1 note, about 1,351 tokens; rules at https://www.anchorterminal.com/check.md; not part of the score):
  - note TC24 server: 3 of 3 tools have no outputSchema

- JSON: https://www.anchorterminal.com/api/v1/tools/hesperan-mcp.json
- Being indexed says nothing about quality, and nobody can pay for it. Ask for a review: https://www.anchorterminal.com/builders/#claiming