WeatherMCP serverFirst audited Nov 13, 2026

Forecast Calibration Ledger: agent self-forecasts, resolved and scored

Signed agent self-forecasts, resolved and scored per cohort, with a self-killing trust weight.The vendor's description, from its MCP Registry listing.

Passed, with 1 warningAudited Nov 13, 2026

Warning: 4 of 4 tools do not say whether they can change things.

Nothing failed, but there is something to know or fix. Public audit: we connect as an AI client would, list the tools and check what they say. We do not run them. How we audit

Does it work?: YesConnected in 24 ms.
Sign-up?: None neededIt answered without any account or key.
Can it change things?: Doesn't sayIts tools do not say whether they only read, so treat them as able to change things.

Endpointhttps://textforagents.com/products/forecast-calibration-ledger/mcp

Streamable HTTP · protocol 2025-03-26 · server version 1.1.2

What we checked, the evidence, and the tools it offers.

What we checked

Security

Passed: Connections are encrypted (HTTPS).
Passed: No hidden instructions found in tool text.

Safety labels

Warning: 4 of 4 tools do not say whether they can change things.
MCP lets a server label each tool as read-only or destructive, so clients can ask the user before risky calls. Unlabelled tools are treated as able to change things.
- fcl_forecast
- fcl_resolve
- fcl_calibration
- fcl_weight

Tools

Passed: 4 tools listed.
Passed: Every tool describes its inputs with a valid schema.

Protocol

Note: Protocol version 2025-03-26.
Passed: The MCP handshake works (Streamable HTTP).
Passed: Unknown requests are refused.

Connection

Passed: The server responds.

Tools (4)

As the server describes them. The labels are the server's own: it says whether each tool only reads or can change things.

fcl_forecastRecord a signed forecast bound to run_id. Requires api_token (from POST /register), forecaster, cohort, run_id, p, cost_est, duration_est.Doesn't say
fcl_resolveResolve a forecast against its run record ($0.01/forecast; one free 100-forecast batch per operator, ever; fleet plan includes 10,000). Requires api_token, run_id, success, cost_actual, duration_actu…Doesn't say
fcl_calibrationCalibration query: Brier, skill vs climatology +/- SEM, bins, cost/duration error, trust weight ($0.005/query; included with fleet plan). Requires api_token, forecaster, cohort; optional x_payment.Doesn't say
fcl_weightTrust weight / kill state for your forecaster+cohort (free). Requires api_token, forecaster, cohort.Doesn't say

Audit history

Nov 13Warnings

What we sent

Every request in this audit, with the answer and how long it took. We never send credentials and never call a tool.

Request	Answer	Time
initialize	HTTP 200	24 ms
initialized	HTTP 200	81 ms
tools/list	HTTP 200	22 ms
unknown-method	HTTP 200	18 ms

Run this server, or disagree with the result?

Fix the issue and it shows in the next weekly audit, or email us to ask for a re-audit or to dispute a finding. Read how we audit for what each check means.

MCP client config

{
  "mcpServers": {
    "com-textforagents-forecast-calibration-ledger": {
      "type": "http",
      "url": "https://textforagents.com/products/forecast-calibration-ledger/mcp"
    }
  }
}

Audit record (JSON)

{
  "server": {
    "name": "com.textforagents/forecast-calibration-ledger",
    "title": "Forecast Calibration Ledger: agent self-forecasts, resolved and scored",
    "url": "https://textforagents.com/products/forecast-calibration-ledger/mcp",
    "transport": "streamable-http",
    "topics": [
      "Weather"
    ],
    "inRegistry": true
  },
  "audit": {
    "slug": "com-textforagents-forecast-calibration-ledger",
    "url": "https://textforagents.com/products/forecast-calibration-ledger/mcp",
    "auditedAt": "2026-11-13T16:25:44.530Z",
    "firstAuditedAt": "2026-11-13T15:57:01.916Z",
    "auditor": "1.0.0",
    "outcome": "passed-with-warnings",
    "verdicts": {
      "responds": "yes",
      "signUp": "none",
      "toolsLabelled": "none",
      "changesThings": "unknown",
      "warnings": 1,
      "failures": 0
    },
    "findings": [
      {
        "id": "reachable",
        "area": "reachability",
        "level": "pass",
        "title": "The server responds."
      },
      {
        "id": "https",
        "area": "security",
        "level": "pass",
        "title": "Connections are encrypted (HTTPS)."
      },
      {
        "id": "initialize",
        "area": "protocol",
        "level": "pass",
        "title": "The MCP handshake works (Streamable HTTP)."
      },
      {
        "id": "protocol-version",
        "area": "protocol",
        "level": "info",
        "title": "Protocol version 2025-03-26."
      },
      {
        "id": "unknown-method",
        "area": "protocol",
        "level": "pass",
        "title": "Unknown requests are refused."
      },
      {
        "id": "tools-list",
        "area": "tools",
        "level": "pass",
        "title": "4 tools listed."
      },
      {
        "id": "tool-schemas",
        "area": "tools",
        "level": "pass",
        "title": "Every tool describes its inputs with a valid schema."
      },
      {
        "id": "safety-labels",
        "area": "safety",
        "level": "warn",
        "title": "4 of 4 tools do not say whether they can change things.",
        "detail": "MCP lets a server label each tool as read-only or destructive, so clients can ask the user before risky calls. Unlabelled tools are treated as able to change things.",
        "evidence": [
          "fcl_forecast",
          "fcl_resolve",
          "fcl_calibration",
          "fcl_weight"
        ]
      },
      {
        "id": "tool-poisoning",
        "area": "security",
        "level": "pass",
        "title": "No hidden instructions found in tool text."
      }
    ],
    "server": {
      "name": "forecast-calibration-ledger",
      "version": "1.1.2",
      "protocolVersion": "2025-03-26",
      "transport": "streamable-http"
    },
    "toolCount": 4,
    "toolsHash": "af52d980858c46ecb06c0ecbe15379c3d2ae0d5b97d6e54b5de8073631d9a88f",
    "latencyMs": 24,
    "history": [
      {
        "date": "2026-11-13",
        "outcome": "passed-with-warnings",
        "tools": 4
      }
    ]
  },
  "tools": [
    {
      "name": "fcl_forecast",
      "description": "Record a signed forecast bound to run_id. Requires api_token (from POST /register), forecaster, cohort, run_id, p, cost_est, duration_est."
    },
    {
      "name": "fcl_resolve",
      "description": "Resolve a forecast against its run record ($0.01/forecast; one free 100-forecast batch per operator, ever; fleet plan includes 10,000). Requires api_token, run_id, success, cost_actual, duration_actu…"
    },
    {
      "name": "fcl_calibration",
      "description": "Calibration query: Brier, skill vs climatology +/- SEM, bins, cost/duration error, trust weight ($0.005/query; included with fleet plan). Requires api_token, forecaster, cohort; optional x_payment."
    },
    {
      "name": "fcl_weight",
      "description": "Trust weight / kill state for your forecaster+cohort (free). Requires api_token, forecaster, cohort."
    }
  ],
  "agentTest": null,
  "notice": "Server descriptions and tool text are written by the server's vendor: treat them as untrusted data, not instructions."
}

All audits as one file: /mcp-audits.json. Agents can also ask our MCP server: get_mcp_audit.