Skip to main content
Glama

costwright — MCP server

Static worst-case token-budget analysis for LLM-agent workflows. Point it at a Python repo using LangGraph / CrewAI / OpenAI-Agents-SDK and it reports — by pure AST analysis, without running the code — the worst-case budget ceiling of every workflow graph: which units are certifiable / default-dependent / non-certifiable / runaway, and which LLM calls have no token cap. Optionally issues an Ed25519-signed budget certificate logged to a public transparency log. Wraps the hosted costwright API; backed by a Lean 4 cost-soundness theorem.

Use it before deploying an agent workflow to catch missing token caps and while True: runaway drivers — the budget version of a type check.

Tools

Tool

What it does

Key?

costwright_check(repo_path, policy?)

Static budget analysis of a local repo. Returns pass/fail + counts of certifiable/default-dependent/non-certifiable/runaway units.

yes

costwright_certify(repo_path, policy?, label?)

Issues a signed, logged budget certificate. Returns cert_id + signature + verify_url.

yes

costwright_verify(cert_id)

Verify a certificate by id (valid/expired/revoked, signature check).

public

costwright_pubkey()

Active Ed25519 public keys for offline verification.

public

Related MCP server: cycles-mcp-server

Setup

{
  "mcpServers": {
    "costwright": {
      "command": "npx",
      "args": ["-y", "costwright-mcp"],
      "env": { "COSTWRIGHT_API_KEY": "your_rapidapi_key" }
    }
  }
}

The key is sent as X-RapidAPI-Key (RapidAPI channel) by default; set COSTWRIGHT_DIRECT=1 to send it as Authorization: Bearer for the direct channel. verify and pubkey work with no key.

check/certify build a .py-only gzip archive of repo_path client-side (excluding venv, node_modules, tests, etc.) and send it for analysis — your source is uploaded to the hosted API. See https://eleata.io/privacy/. MIT licensed.

Available Tools

4 tools
costwright_certifyA

Issue a tamper-evident, Ed25519-signed budget certificate for an agent repo (re-run server-side, logged to a public transparency log). Same input as costwright_check plus an optional label. Returns the cert_id, the signed certificate and a verify_url. Use to produce an auditable proof of a workflow's worst-case spend ceiling.

Inputs: repo_path (required), label, policy.

costwright_checkA

Statically analyze an LLM-agent repo (LangGraph / CrewAI / OpenAI-Agents-SDK) for runaway-budget risk WITHOUT running it. Builds a .py-only archive of the given local path and returns a worst-case budget summary: counts of certifiable / default_dependent / non_certifiable / runaway graph units and a pass|fail verdict. Use before deploying a workflow to catch missing token caps and while-True runaway drivers.

Inputs: repo_path (required), policy.

costwright_pubkeyA

Fetch costwright's active Ed25519 public keys (PEM) for offline signature verification of any certificate (public, no key).

Inputs: no named parameters.

costwright_verifyA

Verify a previously issued costwright certificate by id (public, no key). Returns its state (valid|expired|revoked|signature_invalid), whether the signature checks out, and the certified result.

Inputs: cert_id (required).

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A4.3/5.0

    Scored across 4 tools

    Disambiguation5/5

    Each tool has a clearly distinct purpose: check analyzes budget risk, certify issues a certificate, pubkey retrieves public keys, and verify validates a certificate. No overlap in functionality.

    Naming Consistency5/5

    All tools follow the consistent pattern 'costwright_' plus a verb or noun suffix (check, certify, pubkey, verify), making them easy to distinguish and predict.

    Tool Count5/5

    With 4 tools, the server is well-scoped for its purpose of budget certification. Each tool is necessary and sufficient for the core workflow.

    Completeness4/5

    The set covers the essential operations: checking, certifying, verifying, and key retrieval. Minor gaps like revocation or listing are not critical for the primary use case.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      B
      maintenance
      TACIT (Tracked Agent Capabilities In Types) is a safety harness for AI agents. Instead of calling tools directly, agents write code in Scala 3 with capture checking: a type system that statically tracks capabilities and enforces that agent code cannot forge access rights, cannot perform effects beyond its budget, and cannot leak information from pure sub-computations. It provides an MCP interface,
      149
      Apache 2.0
    • A
      license
      A
      quality
      B
      maintenance
      Runtime budget authority for autonomous agents - a set of tools to check, reserve, spend, and release budget before and after every costly, risky operation. The agent asks "can I afford this?" before acting, and reports what it actually used afterward.
      9
      57 npm
      Apache 2.0