# claimseed (npm · @claimseed/mcp)

Synthetic US medical-billing documents (PDF and ground truth) for testing extractors and agents

- Trust score: 85/100 (high trust)
- Change this week: +18
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- npm · `@claimseed/mcp`: 85/100 (this document), [markdown](https://verifymcp.io/servers/claimseed-claimseed/claimseed-mcp.md), [page](https://verifymcp.io/servers/claimseed-claimseed/claimseed-mcp)

## Channel facts

- Registry: `npm`
- Package: `@claimseed/mcp`
- Version: `0.5.0`
- 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 2026-11-05.

- **Supply Chain Security**: 98/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - No install/post-install scripts declared.
  - 40 of 145 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 100/100
  - Source repository is publicly reachable at the declared URL.
  - Cryptographically verified build provenance (signed, bound to claimseed/claimseed).
  - Clear OSI-approved license (Apache-2.0).
  - Actively maintained (last published 1 days ago).
  - Publishes a security disclosure policy (SECURITY.md).
- **Schema Quality & AI Usability**: 78/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 1987 tokens (~152/item across 13 items; 6 tools + 7 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 23/100
  - Stability observed for 7 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 6 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 8 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.
  - Supports UI / widget rendering.

## Install

### How do I install the claimseed MCP server?

claimseed runs locally as an npm package, launched with npx -y @claimseed/mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add claimseed-claimseed -- npx -y @claimseed/mcp
```

### Cursor

```json
{
  "mcpServers": {
    "claimseed-claimseed": {
      "command": "npx",
      "args": [
        "-y",
        "@claimseed/mcp"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "claimseed-claimseed": {
      "command": "npx",
      "args": [
        "-y",
        "@claimseed/mcp"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add claimseed-claimseed -- npx -y @claimseed/mcp
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add claimseed-claimseed --command npx --arg -y --arg @claimseed/mcp
```

### Hermes

```yaml
mcp_servers:
  claimseed-claimseed:
    command: "npx"
    args: ["-y", "@claimseed/mcp"]
```

### Netclaw

```json
{
  "McpServers": {
    "claimseed-claimseed": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "@claimseed/mcp"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add claimseed-claimseed -t stdio -c npx -a -y @claimseed/mcp
```

### Other

```json
{
  "mcpServers": {
    "claimseed-claimseed": {
      "command": "npx",
      "args": [
        "-y",
        "@claimseed/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.

### 2026-11-05 (score 85, +1)

No change was recorded against any check on this day. Stability & Change Management went from 20 to 23. That category is still filling its 30-day observation window: 6 days of observed history at the previous scan, 7 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-04 (score 84, +11)

- [security improvement] Known CVEs: unverified → pass
- [functional improvement] Dependency health: unverified → 0.87

### 2026-11-03 (score 73, −11)

- [security regression] Known CVEs: pass → unverified
- [functional regression] Schema quality: 125 → 152
- [functional regression] Dependency health: 0.87 → unverified
- [functional] Package version: 0.4.0 → 0.5.0

### 2026-11-02 (score 84, +1)

No change was recorded against any check on this day. Stability & Change Management went from 10 to 13. That category is still filling its 30-day observation window: 3 days of observed history at the previous scan, 4 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-01 (score 83, +1)

- [security regression] Tool safety: pass → unverified
- [security] Stability: Stability not yet verified: we do not have a sandbox capture of the MCP schema this version of the package serves yet.
- [functional regression] Capabilities: pass → unverified
- [functional regression] Tool coverage: 100 → unverified
- [functional regression] Schema quality: 100 → unverified
- [functional regression] Schema quality: pass → fail
- [functional improvement] Stability: unverified → 0.10
- [functional] Package version: 0.3.0 → 0.4.0

### 2026-10-30 (score 82, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-10-29 (score 67, +18)

- [security regression] Malware scan: pass → unverified
- [security improvement] Injection markers: unverified → pass
- [security] First check of Judged manipulation: pass
- [security] Stability: Stability not yet verified: not enough scan history yet (needs a 30-day window).
- [functional improvement] Tool coverage: unverified → 100
- [functional improvement] MCP protocol: unverified → pass
- [functional improvement] Schema quality: unverified → 100
- [functional] First check of Schema quality: fail
- [functional] First check of Destructive annotations: pass
- [functional] First check of Capabilities: pass
- [functional] First check of Schema quality: pass
- [functional] First check of Schema quality: good
- [functional] First check of Tool coverage: 100
- [functional] First check of Tool coverage: 100
- [functional] Package version: 0.1.0 → 0.3.0

### 2026-10-28 (score 49)

First indexed and scored.

## MCP tools (6)

### `list_document_types` (~29 tokens)

List document types

List the document types claimseed can render, each with a short description and its scenario slugs.

Output parameters:

- `types` (array)

### `describe_document_type` (~123 tokens)

Describe a document type

Describe one document type: every scenario with its description, period, number of claims, the errors it injects (kind, severity, rule), its decoys (lines that look wrong but follow the rules) and its public sources. It also lists the type's layout variant ids, which layout_variant accepts besides seeded (an empty list for msn, which has one layout). A scenario with neither errors nor decoys is a clean control.

Input parameters:

- `type` (string, required): document type: msn, itemized-bill, ppo-eob, hmo-eob

Output parameters:

- `description` (string)
- `groundTruthSchema` (string)
- `layoutVariants` (array)
- `orientation` (string)
- `scenarios` (array)
- `title` (string)
- `type` (string)

### `generate_data` (~184 tokens)

Generate document data

Generate the data and ground truth of one document without rendering it (no file is saved). The same type, scenario and seed always give the same result. Every value is synthetic.

Input parameters:

- `layout_variant` (string): Optional. A layout variant id from this document type's published list, or seeded to pick one from the seed. Applies only to itemized-bill, ppo-eob and hmo-eob. Leave it out for the standard layout,…
- `scenario` (string, required): scenario slug, e.g. baseline-clean (see describe_document_type)
- `seed` (string): any short string (letters, digits, . _ -); the same seed always gives the same document
- `type` (string, required): document type: msn, itemized-bill, ppo-eob, hmo-eob

Output parameters:

- `data` (object)
- `groundTruth` (object)

### `render_document` (~368 tokens)

Render a document to PDF

Render one document and return it in the result: its pages as images (as many as fit; from_page shows the rest), the ground truth, the PDF's SHA-256 and page count, and the PDF itself when include_pdf is set and it fits within the size limit. No file is saved. Every page carries specimen markers.

Input parameters:

- `also` (string): 835: also write the X12 835 remittance of the same claims (msn, ppo-eob and hmo-eob only), as a file in the workspace or as text in the result
- `from_page` (integer): first page to return as an image (default 1)
- `include_pdf` (boolean): also return the PDF itself, embedded in the result; it counts toward the same size limit as the page images and is left out, with a note, when it alone is over it
- `layout_variant` (string): Optional. A layout variant id from this document type's published list, or seeded to pick one from the seed. Applies only to itemized-bill, ppo-eob and hmo-eob. Leave it out for the standard layout,…
- `preview` (string): pages returned as images: none, the first (from from_page), or all from from_page on, as many as fit in one result (default all)
- `scenario` (string, required): scenario slug, e.g. baseline-clean (see describe_document_type)
- `seed` (string): any short string (letters, digits, . _ -); the same seed always gives the same document
- `type` (string, required): document type: msn, itemized-bill, ppo-eob, hmo-eob

Output parameters:

- `bytes` (number)
- `degradation` (string|null)
- `groundTruth` (object)
- `groundTruthFile` (string|null)
- `pages` (number)
- `pdf` (string|null)
- `pdfEmbedded` (boolean)
- `preview` (object)
- `remittance`
- `scenario` (string)
- `seed` (string)
- `sha256` (string)
- `type` (string)

### `degrade_document` (~392 tokens)

Render a scanned-looking copy of a document

Render a degraded copy of one document and return it: a flatbed scan, a fax, a phone photo or a low-resolution copy (preset), as an image-only PDF with the specimen band and watermark drawn on top of the degraded pages. The settings come from the seed and are recorded in the ground truth (degradation, degradationParams); the fields are those of the clean document. Returns page images (as many as fit), the ground truth, and the PDF itself when include_pdf is set and it fits. No file is saved.

Input parameters:

- `from_page` (integer): first page to return as an image (default 1)
- `include_pdf` (boolean): also return the degraded PDF itself; it counts toward the same size limit as the page images and is left out, with a note, when it alone is over it
- `layout_variant` (string): Optional. A layout variant id from this document type's published list, or seeded to pick one from the seed. Applies only to itemized-bill, ppo-eob and hmo-eob. Leave it out for the standard layout,…
- `preset` (string, required): scan (flatbed scan), fax (black and white, standard or fine), photo (phone photo of the page on a table) or low-res
- `preview` (string): pages returned as images: none, the first (from from_page), or all from from_page on, as many as fit in one result (default all)
- `scenario` (string, required): scenario slug, e.g. baseline-clean (see describe_document_type)
- `seed` (string): any short string (letters, digits, . _ -); the same seed always gives the same document
- `type` (string, required): document type: msn, itemized-bill, ppo-eob, hmo-eob

Output parameters:

- `bytes` (number)
- `degradation` (string|null)
- `groundTruth` (object)
- `groundTruthFile` (string|null)
- `pages` (number)
- `pdf` (string|null)
- `pdfEmbedded` (boolean)
- `preview` (object)
- `scenario` (string)
- `seed` (string)
- `sha256` (string)
- `type` (string)

### `verify_document` (~404 tokens)

Score an extractor against a document

Score what an extractor or bill auditor reported about one document against its answer key, rebuilt from the type, scenario and seed with this version of claimseed. The report uses the answer key's vocabulary (schema://extractor-output): `fields` maps field paths of documents[0].fields to the values read; `errors` lists flagged errors as { kind, fieldRef or lineRef }. Returns field accuracy with the paths read wrong or missed, error recall and precision, false alarms, and which decoys were flagged. The result names only answer-key paths, kinds and decoy ids, never the text sent. Nothing is rendered or written.

Input parameters:

- `layout_variant` (string): Optional. A layout variant id from this document type's published list, or seeded to pick one from the seed. Applies only to itemized-bill, ppo-eob and hmo-eob. Leave it out for the standard layout,…
- `output` (object, required): the extractor's report (schema://extractor-output). What an extractor or bill auditor reports about one claimseed document, for scoring with `claimseed-core verify` or the MCP tool verify_document. I…
- `scenario` (string, required): scenario slug, e.g. baseline-clean (see describe_document_type)
- `seed` (string): any short string (letters, digits, . _ -); the same seed always gives the same document
- `type` (string, required): document type: msn, itemized-bill, ppo-eob, hmo-eob

Output parameters:

- `answerKey` (object)
- `errors`
- `fields`

## Diagnostics

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

## Score history

- 2026-11-05: 85
- 2026-11-04: 84
- 2026-11-03: 73
- 2026-11-02: 84
- 2026-11-01: 83
- 2026-10-31: 82
- 2026-10-30: 82
- 2026-10-29: 67
- 2026-10-28: 49

## Common questions

### What is the claimseed MCP server?

claimseed is an MCP server listed in the public MCP registry as io.github.claimseed/claimseed. Synthetic US medical-billing documents (PDF and ground truth) for testing extractors and agents. This page covers its npm package (@claimseed/mcp).

### Is the claimseed MCP server safe to use?

claimseed scores 85 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 5 November 2026. It declares no install or post-install scripts. Its build provenance is signed and verified. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the claimseed MCP server expose?

claimseed exposes 6 tools: list_document_types, describe_document_type, generate_data, render_document, degrade_document, verify_document. Their descriptions and schemas cost roughly 1,500 tokens of context every time the server is loaded.

### Is the claimseed MCP server still maintained?

claimseed is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What licence is the claimseed MCP server under?

claimseed declares the Apache-2.0 licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

## Links

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