maap
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
maap-mcp
maap over MCP: ask for a number, get a calibrated distribution — a median, the range the true value should fall inside, and the probability of crossing a threshold you name.
Two tools:
Tool | Does |
| Search the 104 trained targets. Call this first — a target id is not guessable |
| One case, one target → median, quantiles, intervals, |
Install
Get a key at dash.hitl.systems/keys, then add the server to your client.
Claude Desktop — claude_desktop_config.json:
{
"mcpServers": {
"maap": {
"command": "npx",
"args": ["-y", "maap-mcp"],
"env": { "MAAP_API_KEY": "apikey_..." }
}
}
}Claude Code:
claude mcp add maap --env MAAP_API_KEY=apikey_... -- npx -y maap-mcpNot on npm yet — until it is, install straight from this repo by swapping maap-mcp for
github:hitl-systems/maap-mcp in any of the above. The built bundle is committed, so there is
nothing to compile.
Cursor — ~/.cursor/mcp.json: the same mcpServers block as Claude Desktop.
Variable | Required | Default |
| yes | — |
| no |
|
Related MCP server: jev-code
Using it
Which maap target predicts flight prices? Estimate the fare for a Vistara economy ticket Delhi → Mumbai, non-stop, booked 9 days out, and tell me the chance it is over ₹10,000.
The agent calls list_targets for the id, then estimate with your case as the state.
Read the median as the answer and the range as what to plan against. For a threshold
question, pass thresholds and read P(value > t) — do not compare the median to the
threshold yourself; the median says where the middle is, not how likely the threshold is.
An answer also carries how much to trust it: regime (in_domain, or new_target when the
model only knows what your examples taught it), calibration ("none" means no correction
survived its check, so the range carries no coverage promise), and novelty_flag when the case
is unlike anything in training. Known limits are published:
dash.hitl.systems/docs/calibration.
Notes
One question per call. The HTTP API takes up to 32 under names you choose; a flat tool is the one an agent fills in correctly.
The first call after an idle period starts a GPU container and can take tens of seconds. The server waits 120 s and tells the agent to retry rather than failing silently.
Each question counts against your allowance. A rejected call costs nothing.
Pricing, limits and the full wire format: dash.hitl.systems/docs/api.
MIT.
This server cannot be deployed
Maintenance
Related MCP Connectors
Decision models for agents over x402: yes/no, choice and score questions as probabilities, per call.
Calibrated judgments for text: yes/no probabilities, picks from your options, or scores.
Commit-pace and release probabilities for open-source repositories. For each repository it covers, Anteproof publishes two dated probabilities: will it reach its commit target, and will it publish a release, in the 90 days from the day the question is issued. Search entities, read their open questions and latest forecasts, and check the calibration page for what is scored and what is withheld. Listing the tools works without a key; calling one needs an API key. A probability is not advice.
Calibrated probabilistic foresight for AI agents, powered by live prediction-market signal.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceEnables agents to evaluate single records or batches with dynamically authored typed questions, returning structured decisions and probabilities.23 PyPIMIT
- AlicenseNot gradedqualityAmaintenanceProvides coding agents with typed classification, yes/no checks, scoring, ranking, and question-answering tools that return calibrated probabilities for fast, reliable decisions.818 npm56MIT
- AlicenseNot gradedqualityBmaintenanceEnables coding agents to make confident decisions using calibrated probabilistic tools for screening, verification, ranking, classification, and gating, fully self-hosted as an optional MCP server.123 npm1MIT
- AlicenseAqualityBmaintenanceEnables MCP clients to get calibrated probability judgments for choice, score, yes/no, and batch classification questions via the TypeSafe System One API.5100 PyPI3MIT