# Weishengxin — 微生信 (remote · www.bioinformatics.com.cn)

Scientific plotting for bioinformatics with about 160 free modules. Anonymous access supported.

- Trust score: 65/100 (medium)
- Change this week: +6
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-21

## Components

- remote · `www.bioinformatics.com.cn`: 65/100 (this document), [markdown](https://verifymcp.io/servers/cn-com-bioinformatics-weishengxin/www.md), [page](https://verifymcp.io/servers/cn-com-bioinformatics-weishengxin/www)

## Channel facts

- Endpoint: `https://www.bioinformatics.com.cn/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.0.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, 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 2026-11-21.

- **Endpoint Security**: 46/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation not fully verified: no authorisation is required to call this server, and 11 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.
  - HTTPS enforcement could not be verified: the plaintext port answered with HTTP 404, which proves neither a plaintext path nor enforcement.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 62/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 4010 tokens (~364/item across 11 items; 11 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 50/100
  - Stability observed for 15 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 11 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 12 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.

## Install

### How do I install the Weishengxin — 微生信 MCP server?

Weishengxin — 微生信 is a hosted endpoint at https://www.bioinformatics.com.cn/mcp, so there is nothing to install locally. 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 --transport http cn-com-bioinformatics-weishengxin 'https://www.bioinformatics.com.cn/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "cn-com-bioinformatics-weishengxin": {
      "url": "https://www.bioinformatics.com.cn/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "cn-com-bioinformatics-weishengxin": {
      "type": "http",
      "url": "https://www.bioinformatics.com.cn/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.cn-com-bioinformatics-weishengxin]
url = "https://www.bioinformatics.com.cn/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "cn-com-bioinformatics-weishengxin": {
      "type": "remote",
      "url": "https://www.bioinformatics.com.cn/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add cn-com-bioinformatics-weishengxin --url 'https://www.bioinformatics.com.cn/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  cn-com-bioinformatics-weishengxin:
    url: "https://www.bioinformatics.com.cn/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "cn-com-bioinformatics-weishengxin": {
      "Transport": "http",
      "Url": "https://www.bioinformatics.com.cn/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add cn-com-bioinformatics-weishengxin -t streamable-http -u 'https://www.bioinformatics.com.cn/mcp'
```

### Other

```json
{
  "mcpServers": {
    "cn-com-bioinformatics-weishengxin": {
      "type": "http",
      "url": "https://www.bioinformatics.com.cn/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## 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.

### 2026-11-21 (score 65, +1)

No change was recorded against any check on this day. Stability & Change Management went from 47 to 50. That category is still filling its 30-day observation window: 14 days of observed history at the previous scan, 15 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-19 (score 64, +4)

- [security improvement] Injection markers: unverified → pass
- [security] Authorization: Authorisation not fully verified: no authorisation is required to call this server, and 11 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.
- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “append_file_chunk” rewrote its description, which is the text the model reads
- [security] Tool “begin_file_upload” rewrote its description, which is the text the model reads
- [security] Tool “draw_plot” rewrote its description, which is the text the model reads
- [security] Tool “finish_file_upload” rewrote its description, which is the text the model reads
- [security] Tool “get_faq” rewrote its description, which is the text the model reads
- [security] Tool “get_module_demo” rewrote its description, which is the text the model reads
- [security] Tool “get_module_schema” rewrote its description, which is the text the model reads
- [security] Tool “get_result” rewrote its description, which is the text the model reads
- [security] Tool “get_upload_info” rewrote its description, which is the text the model reads
- [security] Tool “list_modules” rewrote its description, which is the text the model reads
- [security] Tool “upload_file” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: 246 → 364
- [functional improvement] Endpoint reachability: unreachable → reachable
- [functional improvement] Tool coverage: 47% → 100%
- [functional improvement] Tool coverage: unverified → 100
- [functional improvement] Stability: unverified → 0.43
- [functional improvement] MCP protocol: unverified → pass
- [functional] Schema quality: good → excellent
- [cosmetic] “append_file_chunk” reworded the description of “content_base64”
- [cosmetic] “append_file_chunk” reworded the description of “file_id”
- [cosmetic] “append_file_chunk” reworded the description of “input_name”
- [cosmetic] “append_file_chunk” reworded the description of “module_id”
- [cosmetic] “append_file_chunk” reworded the description of “offset”
- [cosmetic] “begin_file_upload” reworded the description of “filename”
- [cosmetic] “begin_file_upload” reworded the description of “input_name”
- [cosmetic] “begin_file_upload” reworded the description of “module_id”
- [cosmetic] “draw_plot” reworded the description of “data_tsv”
- [cosmetic] “draw_plot” reworded the description of “module_id”
- [cosmetic] “draw_plot” reworded the description of “params”
- [cosmetic] “draw_plot” reworded the description of “request_id”
- [cosmetic] “finish_file_upload” reworded the description of “file_id”
- [cosmetic] “finish_file_upload” reworded the description of “input_name”
- [cosmetic] “finish_file_upload” reworded the description of “module_id”
- [cosmetic] “get_faq” reworded the description of “keyword”
- [cosmetic] “get_module_demo” reworded the description of “module_id”
- [cosmetic] “get_module_schema” reworded the description of “module_id”
- [cosmetic] “get_result” reworded the description of “request_id”
- [cosmetic] “get_upload_info” reworded the description of “input_name”
- [cosmetic] “get_upload_info” reworded the description of “module_id”
- [cosmetic] “list_modules” reworded the description of “keyword”
- [cosmetic] “upload_file” reworded the description of “content_base64”
- [cosmetic] “upload_file” reworded the description of “filename”
- [cosmetic] “upload_file” reworded the description of “input_name”
- [cosmetic] “upload_file” reworded the description of “module_id”

### 2026-11-18 (score 60, 0)

- [security regression] Endpoint reachability: reachable → unreachable
- [security regression] Stability: 0.37 → unverified
- [security regression] Tool safety: pass → unverified
- [security] Authorization: Authorisation not fully verified: no authorisation is required to connect, but we couldn't read the whole tool list to see what that exposes.
- [functional regression] Capabilities: pass → unverified
- [functional regression] Tool coverage: 100 → unverified
- [functional] First check of Schema quality: unverified

### 2026-11-16 (score 60, +1)

No change was recorded against any check on this day. Stability & Change Management went from 30 to 33. That category is still filling its 30-day observation window: 9 days of observed history at the previous scan, 10 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-15 (score 59, 0)

- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “append_file_chunk” rewrote its description, which is the text the model reads

### 2026-11-14 (score 59, +1)

- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “draw_plot” rewrote its description, which is the text the model reads

### 2026-11-12 (score 58, 0)

- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “get_module_demo” rewrote its description, which is the text the model reads
- [security] Tool “get_result” rewrote its description, which is the text the model reads
- [security] Tool “get_upload_info” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: 204 → 240
- [cosmetic] “draw_plot” reworded the description of “data_tsv”
- [cosmetic] “draw_plot” reworded the description of “params”

### 2026-11-11 (score 58, 0)

- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “draw_plot” rewrote its description, which is the text the model reads
- [security] Tool “get_upload_info” rewrote its description, which is the text the model reads

## MCP tools (11)

### `get_upload_info` (~184 tokens)

Return the upload endpoint, allowed extensions, size limits and authentication instructions for module_id and input_name. / 返回指定模块输入的上传地址、支持扩展名、大小限制和认证说明。

Input parameters:

- `input_name` (string): Exact key from get_module_schema.inputs. The default file uses the sole input if there is no file key. For multiple inputs, use the exact key and keep it the same throughout the upload. / 使用 inputs 中…
- `module_id` (string, required): Exact ID from the modules mapping returned by list_modules. For execution or upload, choose an available module. / 使用 list_modules 返回的 modules 对象中的准确键名；执行或上传须选可用模块。

### `upload_file` (~326 tokens)

Upload filename in one MCP call using content_base64 for module_id and input_name. Return file_id, bytes, sha256 and a ready-to-use data_tsv mapping. / 一次上传完整小文件，返回文件编号、字节数、哈希和可直接提交的 data_tsv 映射。

Input parameters:

- `content_base64` (string, required): Standard Base64 of the entire actual file (1 byte to 1 MiB decoded). Supply only the encoded bytes, with no line breaks or data URL prefix. / 真实文件完整字节的标准 Base64，解码后 1 字节至 1 MiB；只传编码内容，不换行、不加 data URL…
- `filename` (string, required): Original basename with an extension allowed by get_upload_info for this input. / 原文件名须保留允许的扩展名，仅传文件名。
- `input_name` (string): Exact key from get_module_schema.inputs. The default file uses the sole input if there is no file key. For multiple inputs, use the exact key and keep it the same throughout the upload. / 使用 inputs 中…
- `module_id` (string, required): Exact ID from the modules mapping returned by list_modules. For execution or upload, choose an available module. / 使用 list_modules 返回的 modules 对象中的准确键名；执行或上传须选可用模块。

### `begin_file_upload` (~234 tokens)

Start a chunked upload for module_id, input_name and filename. Return file_id, initial next_offset (0), byte limits and expiry. / 创建分块上传，返回文件编号、初始偏移 0、大小限制和过期时间。

Input parameters:

- `filename` (string, required): Original basename with an extension allowed by get_upload_info for this input. / 原文件名须保留允许的扩展名，仅传文件名。
- `input_name` (string): Exact key from get_module_schema.inputs. The default file uses the sole input if there is no file key. For multiple inputs, use the exact key and keep it the same throughout the upload. / 使用 inputs 中…
- `module_id` (string, required): Exact ID from the modules mapping returned by list_modules. For execution or upload, choose an available module. / 使用 list_modules 返回的 modules 对象中的准确键名；执行或上传须选可用模块。

### `append_file_chunk` (~385 tokens)

Append content_base64 at offset for the same module_id, input_name and file_id. Return next_offset and bytes_received. After the last chunk, call finish_file_upload. / 追加分块并返回下一字节偏移和累计字节数；最后一块之后调用 finish_file_upload。

Input parameters:

- `content_base64` (string, required): Standard Base64 of only this chunk (1 byte to 128 KiB decoded). Slice raw file bytes first, then encode each chunk separately. / 先按原始字节切块，再独立做标准 Base64 编码；每块解码后 1 字节至 128 KiB。
- `file_id` (string, required): Use the file_id returned by begin_file_upload for this account, module_id and input_name. / 原样使用当前账号及模块输入对应的 begin_file_upload 返回编号。
- `input_name` (string): Exact key from get_module_schema.inputs. The default file uses the sole input if there is no file key. For multiple inputs, use the exact key and keep it the same throughout the upload. / 使用 inputs 中…
- `module_id` (string, required): Exact ID from the modules mapping returned by list_modules. For execution or upload, choose an available module. / 使用 list_modules 返回的 modules 对象中的准确键名；执行或上传须选可用模块。
- `offset` (integer, required): Zero-based offset in raw bytes. Use next_offset from the last response; on retry reuse the original offset and identical bytes. / 原始字节偏移，从 0 开始，下一块用返回的 next_offset；重试使用原偏移及相同字节。

### `finish_file_upload` (~259 tokens)

Finalize file_id for the same module_id and input_name. Return bytes, sha256, file_id and the data_tsv mapping. Compare bytes and sha256 with the local file before plotting. / 完成上传，返回字节数、哈希、文件编号和 data_tsv 映射；绘图前核对本地文件。

Input parameters:

- `file_id` (string, required): Use the file_id returned by begin_file_upload for this account, module_id and input_name. / 原样使用当前账号及模块输入对应的 begin_file_upload 返回编号。
- `input_name` (string): Exact key from get_module_schema.inputs. The default file uses the sole input if there is no file key. For multiple inputs, use the exact key and keep it the same throughout the upload. / 使用 inputs 中…
- `module_id` (string, required): Exact ID from the modules mapping returned by list_modules. For execution or upload, choose an available module. / 使用 list_modules 返回的 modules 对象中的准确键名；执行或上传须选可用模块。

### `list_modules` (~184 tokens)

Search the module catalog by keyword, or browse with an empty keyword. Use offset and limit to page. Return summaries keyed by module ID, with availability and next_offset. Only available=true entries can run. / 检索或分页浏览模块，返回以模块编号为键的摘要、可用性和下一页偏移；available=true 的模块可运行。

Input parameters:

- `keyword` (string): Module search terms such as purpose, data columns or plot name. All space-separated terms must match. / 用途、数据列或图名等模块检索词，空格分词全部匹配。
- `limit` (integer): Modules per page, 1–50. / 每页模块数，1～50。
- `offset` (integer): Zero-based pagination offset; use next_offset. / 分页起点，使用返回的 next_offset。

### `get_faq` (~176 tokens)

Search common usage and troubleshooting by keyword or exact faq_id. Use offset and limit to page. Return FAQ questions, answers, links, total and next_offset. / 按关键词或编号查询常见问题，返回问答、链接、总数和下一页偏移。

Input parameters:

- `faq_id` (string): Optional exact FAQ ID. / 可选的精确问答编号。
- `keyword` (string): Website usage or troubleshooting search terms. All space-separated terms must match. / 网站使用或排错的问答检索词，空格分词全部匹配。
- `limit` (integer): FAQ entries per page, 1–20. / 每页问答数，1～20。
- `offset` (integer): Zero-based pagination offset. / 从0开始的分页起点。

### `get_module_demo` (~116 tokens)

Return illustrations, demo inputs and full sample downloads for module_id when available. The response marks preview-only data and unavailable links. / 返回模块可用的示意图、示例输入和完整示例下载，并标明仅供预览的数据和不可用链接。

Input parameters:

- `module_id` (string, required): Exact ID from the modules mapping returned by list_modules. For execution or upload, choose an available module. / 使用 list_modules 返回的 modules 对象中的准确键名；执行或上传须选可用模块。

### `get_module_schema` (~153 tokens)

Return inputs, column meanings, examples, parameter aliases, defaults and constraints for module_id. Read before drawing. Set include_details for the full module FAQ. / 返回模块输入、列含义、示例、参数别名、默认值和约束，完整问答按需读取。

Input parameters:

- `include_details` (boolean): Include full module FAQ only when needed; default false. / 需要完整模块问答时设为true，默认false。
- `module_id` (string, required): Exact ID from the modules mapping returned by list_modules. For execution or upload, choose an available module. / 使用 list_modules 返回的 modules 对象中的准确键名；执行或上传须选可用模块。

### `draw_plot` (~444 tokens)

Submit module_id with data_tsv, request_id and optional params. Keep all input data in data_tsv and module settings in params. Return submission status, request_id and poll_after_seconds when queued. Poll get_result with the original ID. Public access uses source IP limits; annual accounts share five unfinished tasks. / 提交绘图，数据放 data_tsv，模块选项放 params；返回受理状态和请求编号，排队时返回轮询间隔。使用原编号查询结果。

Input parameters:

- `data_tsv` (string|object, required): For a single text input, send text directly or use an inputs key-to-text object. For multiple inputs, put all required inputs in one object using exact inputs keys. Use finalized upload mappings for…
- `module_id` (string, required): Exact ID from the modules mapping returned by list_modules. For execution or upload, choose an available module. / 使用 list_modules 返回的 modules 对象中的准确键名；执行或上传须选可用模块。
- `params` (object|null): Module parameter name-to-value object at the top-level params key. Supply required_parameters_without_defaults and requested overrides using names and types from get_module_schema. If none apply, omi…
- `request_id` (string, required): Use a new UUID for each new task. For polling or checking a timeout, reuse the original ID. / 每个新任务用新 UUID；轮询或超时查询沿用原编号。

### `get_result` (~112 tokens)

Return the status and available output file links for the original draw_plot request_id in the current access scope. Use the same ID after timeouts. / 返回当前访问范围内原始 draw_plot 请求的状态和可用文件链接，超时沿用原编号查询。

Input parameters:

- `request_id` (string, required): Use a new UUID for each new task. For polling or checking a timeout, reuse the original ID. / 每个新任务用新 UUID；轮询或超时查询沿用原编号。

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/cn-com-bioinformatics-weishengxin/www#diagnostics

## Score history

- 2026-11-21: 65
- 2026-11-20: 64
- 2026-11-19: 64
- 2026-11-18: 60
- 2026-11-17: 60
- 2026-11-16: 60
- 2026-11-15: 59
- 2026-11-14: 59
- 2026-11-13: 58
- 2026-11-12: 58
- 2026-11-11: 58
- 2026-11-10: 58
- 2026-11-09: 59
- 2026-11-08: 59
- 2026-11-07: 58
- 2026-11-06: 58

## Common questions

### What is the Weishengxin — 微生信 MCP server?

Weishengxin — 微生信 is an MCP server listed in the public MCP registry as cn.com.bioinformatics/weishengxin. Scientific plotting for bioinformatics with about 160 free modules. Anonymous access supported. This page covers its hosted endpoint (https://www.bioinformatics.com.cn/mcp).

### Is the Weishengxin — 微生信 MCP server safe to use?

Weishengxin — 微生信 scores 65 out of 100 on VerifyMCP. 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 Weishengxin — 微生信 MCP server expose?

Weishengxin — 微生信 exposes 11 tools: get_upload_info, upload_file, begin_file_upload, append_file_chunk, finish_file_upload, and 6 more. Their descriptions and schemas cost roughly 2,573 tokens of context every time the server is loaded.

### Does the Weishengxin — 微生信 MCP server require authentication?

No. We connected to Weishengxin — 微生信 without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the Weishengxin — 微生信 MCP server still maintained?

Weishengxin — 微生信 is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What did VerifyMCP test on the Weishengxin — 微生信 MCP server?

VerifyMCP ran 11 checks on Weishengxin — 微生信, covering TLS certificate, HSTS header, DNSSEC, Transport and 7 more. 2 items could not be completed, a gap on our side rather than a finding about Weishengxin — 微生信: Authorization and HTTPS. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- Remote endpoint: https://www.bioinformatics.com.cn/mcp
- Changelog RSS feed: https://verifymcp.io/servers/cn-com-bioinformatics-weishengxin/www.xml
- Changelog JSON feed: https://verifymcp.io/servers/cn-com-bioinformatics-weishengxin/www/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/cn-com-bioinformatics-weishengxin/www.json
- HTML version of this page: https://verifymcp.io/servers/cn-com-bioinformatics-weishengxin/www
