# BioMapper (pypi · biomapper)

Resolve metabolite, lipid, protein, gene and lab names to knowledge-graph IDs.

- Trust score: 52/100 (low)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- pypi · `biomapper`: 52/100 (this document), [markdown](https://verifymcp.io/servers/trentleslie-biomapper/biomapper.md), [page](https://verifymcp.io/servers/trentleslie-biomapper/biomapper)

## Channel facts

- Registry: `pypi`
- Package: `biomapper`
- Version: `1.6.2`
- 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**: 50/100
  - Malware scan not yet available for this package.
  - No known CVEs affecting this package version or its production dependencies.
  - Runs poetry.core.masonry.api at install time, a recognised build step with no custom scripting around it.
  - 2 of 33 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 45/100
  - Source repository is publicly reachable at the declared URL.
  - Build provenance not yet verified.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 0 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 843 tokens (~84/item across 10 items; 10 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 0/100
  - Stability not yet verified: not enough scan history yet (needs a 30-day window).
- **Tool Coverage**: 71/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 0% 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 10 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 11 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

**Unverified: 1 category.** A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

## Install

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

BioMapper runs locally as a PyPI package, launched with uvx biomapper. 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 trentleslie-biomapper -- uvx biomapper
```

### Cursor

```json
{
  "mcpServers": {
    "trentleslie-biomapper": {
      "command": "uvx",
      "args": [
        "biomapper"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "trentleslie-biomapper": {
      "command": "uvx",
      "args": [
        "biomapper"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add trentleslie-biomapper -- uvx biomapper
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "trentleslie-biomapper": {
      "type": "local",
      "command": [
        "uvx",
        "biomapper"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add trentleslie-biomapper --command uvx --arg biomapper
```

### Hermes

```yaml
mcp_servers:
  trentleslie-biomapper:
    command: "uvx"
    args: ["biomapper"]
```

### Netclaw

```json
{
  "McpServers": {
    "trentleslie-biomapper": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "biomapper"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add trentleslie-biomapper -t stdio -c uvx -a biomapper
```

### Other

```json
{
  "mcpServers": {
    "trentleslie-biomapper": {
      "command": "uvx",
      "args": [
        "biomapper"
      ]
    }
  }
}
```

## 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 52)

First indexed and scored.

## MCP tools (10)

### `list_entity_types` (~39 tokens)

List the Biolink entity types BioMapper accepts, with aliases and default identifier prefixes. Call this first to choose entity_type for the mapping tools.

Output parameters:

- `entity_types` (array)

### `list_vocabularies` (~25 tokens)

List the identifier vocabularies (CURIE prefixes) BioMapper knows.

Output parameters:

- `vocabularies` (array)

### `list_annotators` (~22 tokens)

List the annotators the BioMapper mapping pipeline can use.

Output parameters:

- `annotators` (array)

### `server_info` (~38 tokens)

Server version, KG provenance (pending until the startup probe lands), limits, and the folders map_file may read. Makes no request to BioMapper.

Output parameters:

- `allowed_roots` (array)
- `batch_cap` (integer)
- `loop_limit` (integer)
- `loop_window_s` (number)
- `provenance`
- `server_version` (string)

### `map_entity` (~117 tokens)

Map ONE entity name to knowledge-graph identifiers. Takes about 4-5 s. Call list_entity_types first to choose entity_type (e.g. biolink:SmallMolecule for metabolites). Optional identifiers are hints, e.g. {"HMDB": "HMDB0000177"}. For more than 5 entities use map_file instead; repeated single calls are refused after a limit.

Input parameters:

- `annotation_mode` (string)
- `entity_type` (string, required)
- `identifiers`
- `name` (string, required)

Output parameters:

- `provenance`
- `result`

### `map_batch` (~81 tokens)

Map up to 5 entities of one entity_type in a single request (about 4-5 s per entity, so up to ~25 s). More than 5 is refused: write them to a TSV/CSV and use map_file.

Input parameters:

- `annotation_mode` (string)
- `entities` (array, required)
- `entity_type` (string, required)

Output parameters:

- `provenance`
- `results` (array)

### `map_file` (~208 tokens)

Map every row of a TSV/CSV file as a resumable BACKGROUND job and return immediately with a job_id and an ETA (about 4-5 s per unique entity). Use this for more than 5 entities. The file must be inside an allowed folder (the client's roots or BIOMAPPER_MCP_ROOTS). Writes <input>.biomapper.tsv next to the input (never overwrites) plus a provenance JSON. identifier_columns maps a column name to its vocabulary, e.g. {"hmdb_id": "HMDB"}. Re-submitting the same file and options returns the existing job; rerun=true starts over with a fresh cache. Poll job_status about once a minute.

Input parameters:

- `annotation_mode` (string)
- `entity_type` (string, required)
- `identifier_columns`
- `key_column`
- `name_column` (string, required)
- `output_path`
- `path` (string, required)
- `rerun` (boolean)

Output parameters:

- `created_utc` (string)
- `entities_done` (integer)
- `entities_failed` (integer)
- `entities_total` (integer): Unique entities (duplicate rows are mapped once)
- `eta_s`: Best-effort estimate, not a promise
- `input_path` (string)
- `job_id` (string)
- `kg_build` (string)
- `kg_verified` (boolean)
- `output_path` (string)
- `owner`
- `partial_path` (string)
- `pass_index` (integer)
- `provenance_path` (string)
- `reason`
- `rows_total` (integer)
- `state` (string)
- `updated_utc` (string)

### `job_status` (~78 tokens)

Status of one map_file job (job_id) or of all jobs in the current folders: state (queued, running, paused, stalled, expired, cancelled, complete, failed, owned_elsewhere), progress, ETA estimate, output path, and whether the KG build is verified. Makes no request to BioMapper.

Input parameters:

- `job_id`

Output parameters:

- `jobs` (array)
- `note`

### `resume_job` (~42 tokens)

Resume a stalled, expired, paused, or cancelled job after a fresh health check. Rows already mapped are not re-mapped.

Input parameters:

- `job_id` (string, required)

Output parameters:

- `created_utc` (string)
- `entities_done` (integer)
- `entities_failed` (integer)
- `entities_total` (integer): Unique entities (duplicate rows are mapped once)
- `eta_s`: Best-effort estimate, not a promise
- `input_path` (string)
- `job_id` (string)
- `kg_build` (string)
- `kg_verified` (boolean)
- `output_path` (string)
- `owner`
- `partial_path` (string)
- `pass_index` (integer)
- `provenance_path` (string)
- `reason`
- `rows_total` (integer)
- `state` (string)
- `updated_utc` (string)

### `cancel_job` (~43 tokens)

Cancel a job. It stops after the current chunk; the partial output and cache are kept, so resume_job can continue it later.

Input parameters:

- `job_id` (string, required)

Output parameters:

- `created_utc` (string)
- `entities_done` (integer)
- `entities_failed` (integer)
- `entities_total` (integer): Unique entities (duplicate rows are mapped once)
- `eta_s`: Best-effort estimate, not a promise
- `input_path` (string)
- `job_id` (string)
- `kg_build` (string)
- `kg_verified` (boolean)
- `output_path` (string)
- `owner`
- `partial_path` (string)
- `pass_index` (integer)
- `provenance_path` (string)
- `reason`
- `rows_total` (integer)
- `state` (string)
- `updated_utc` (string)

## Diagnostics

Captured diagnostic sections: Provenance, Install scripts, Dependencies. The full working is on the page: https://verifymcp.io/servers/trentleslie-biomapper/biomapper#diagnostics

## Score history

- 2026-11-05: 52

## Common questions

### What is the BioMapper MCP server?

BioMapper is an MCP server listed in the public MCP registry as io.github.trentleslie/biomapper. Resolve metabolite, lipid, protein, gene and lab names to knowledge-graph IDs. This page covers its PyPI package (biomapper).

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

BioMapper scores 52 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 5 November 2026. 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 BioMapper MCP server expose?

BioMapper exposes 10 tools: list_entity_types, list_vocabularies, list_annotators, server_info, map_entity, and 5 more. Their descriptions and schemas cost roughly 693 tokens of context every time the server is loaded.

### Is the BioMapper MCP server still maintained?

BioMapper 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 BioMapper MCP server under?

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

### What did VerifyMCP test on the BioMapper MCP server?

VerifyMCP ran 13 checks on BioMapper, covering Known CVEs, Install scripts, Dependency health, Source repository and 9 more. 3 items could not be completed, a gap on our side rather than a finding about BioMapper: Malware scan, Provenance and Stability. One category scores 0 for that reason, because we only credit what we can confirm. Endpoint Security and Transport & Reachability do not apply to a PyPI package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- PyPI project: https://pypi.org/project/biomapper/
- Socket report: https://socket.dev/pypi/package/biomapper
- Repository: https://github.com/Phenome-Health/biomapper
- Changelog RSS feed: https://verifymcp.io/servers/trentleslie-biomapper/biomapper.xml
- Changelog JSON feed: https://verifymcp.io/servers/trentleslie-biomapper/biomapper/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/trentleslie-biomapper/biomapper.json
- HTML version of this page: https://verifymcp.io/servers/trentleslie-biomapper/biomapper