# costwright — agent budget analysis (npm · costwright-mcp)

Static worst-case token-budget analysis for LLM-agent workflows + signed budget certificates.

- Trust score: 67/100 (medium)
- Change this week: +21
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- npm · `costwright-mcp`: 67/100 (this document), [markdown](https://verifymcp.io/servers/hernaninverso-costwright-mcp/costwright-mcp.md), [page](https://verifymcp.io/servers/hernaninverso-costwright-mcp/costwright-mcp)

## Channel facts

- Registry: `npm`
- Package: `costwright-mcp`
- Version: `0.1.1`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-08-03.

- **Supply Chain Security**: 86/100
  - No malware found by supply-chain analysis.
  - Only part of the dependency tree could be resolved (94 of 98), so this covers what we could see, not the whole tree.
  - No install/post-install scripts declared.
  - Only part of the dependency tree could be resolved (94 of 98), so this covers what we could see, not the whole tree.
- **Provenance & Transparency**: 45/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 33 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 69/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 346 tokens (~86/item across 4 items; 4 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 27/100
  - Stability observed for 8 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 94/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 83% of tool parameters carry a description.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add hernaninverso-costwright-mcp -- npx -y costwright-mcp
```

### Codex

```bash
codex mcp add hernaninverso-costwright-mcp -- npx -y costwright-mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "hernaninverso-costwright-mcp": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "costwright-mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add hernaninverso-costwright-mcp --command npx --arg -y --arg costwright-mcp
```

### Hermes

```yaml
mcp_servers:
  hernaninverso-costwright-mcp:
    command: "npx"
    args: ["-y", "costwright-mcp"]
```

### Other

```json
{
  "mcpServers": {
    "hernaninverso-costwright-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "costwright-mcp"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-08-03 (score 67, +1)

No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-08-02 (score 66, +46)

- [security regression] Provenance: unverified → fail
- [security improvement] Known CVEs: unverified → partial
- [security improvement] Install scripts: unverified → pass
- [security improvement] Malware scan: unverified → pass
- [functional regression] Security disclosure: fail → unverified
- [functional regression] Tool coverage: 100 → unverified
- [functional improvement] License: unverified → pass
- [functional improvement] Dependency health: unverified → partial
- [functional improvement] Maintenance: unverified → pass
- [functional improvement] MCP protocol: unverified → pass
- [functional improvement] Stability: unverified → 0.23
- [functional improvement] Schema quality: unverified → good
- [functional] First check of Schema quality: unverified
- [functional] Licence: MIT

### 2026-07-31 (score 20, −8)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-30 (score 28, −18)

- [security regression] Malware scan: pass → unverified

### 2026-07-27 (score 46)

First indexed and scored.

## MCP tools (4)

### `costwright_check` (~126 tokens)

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.

Input parameters:

- `policy` (string): Analysis policy.
- `repo_path` (string, required): Absolute path to the local Python repo/directory to analyze.

### `costwright_certify` (~121 tokens)

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.

Input parameters:

- `label` (string): Optional human label for the certificate.
- `policy` (string)
- `repo_path` (string, required): Absolute path to the local Python repo/directory to certify.

### `costwright_verify` (~62 tokens)

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.

Input parameters:

- `cert_id` (string, required): The certificate id to verify.

### `costwright_pubkey` (~37 tokens)

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

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/hernaninverso-costwright-mcp/costwright-mcp#diagnostics

## Score history

- 2026-08-03: 67
- 2026-08-02: 66
- 2026-08-01: 20
- 2026-07-31: 20
- 2026-07-30: 28
- 2026-07-28: 46
- 2026-07-27: 46

## Links

- npm package: https://www.npmjs.com/package/costwright-mcp
- Socket report: https://socket.dev/npm/package/costwright-mcp
- Repository: https://github.com/hernaninverso/costwright-mcp
- Changelog RSS feed: https://verifymcp.io/servers/hernaninverso-costwright-mcp/costwright-mcp/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/hernaninverso-costwright-mcp/costwright-mcp/changelog.json
- HTML version of this page: https://verifymcp.io/servers/hernaninverso-costwright-mcp/costwright-mcp