# Markdown Pipeline (pypi · mdpipeline)

Your team's Jira as clean Markdown files, kept current for your AI agent. Local and read-only.

- Trust score: 53/100 (low)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-04

## Components

- pypi · `mdpipeline`: 53/100 (this document), [markdown](https://verifymcp.io/servers/markdown-pipeline-mdpipeline/mdpipeline.md), [page](https://verifymcp.io/servers/markdown-pipeline-mdpipeline/mdpipeline)

## Channel facts

- Registry: `pypi`
- Package: `mdpipeline`
- Version: `0.1.16`
- 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 2026-11-04.

- **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 uv_build at install time, a recognised build step with no custom scripting around it.
  - 1 of 32 dependencies flagged as unhealthy.
- **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 (Apache-2.0).
  - Actively maintained (last published 0 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 66/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 480 tokens (~80/item across 6 items; 6 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 10/100
  - Stability observed for 3 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 67/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 0% of tool parameters carry a description.
- **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 7 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).

## Install

### How do I install the Markdown Pipeline MCP server?

Markdown Pipeline runs locally as a PyPI package, launched with uvx mdpipeline. 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 markdown-pipeline-mdpipeline -- uvx mdpipeline
```

### Cursor

```json
{
  "mcpServers": {
    "markdown-pipeline-mdpipeline": {
      "command": "uvx",
      "args": [
        "mdpipeline"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "markdown-pipeline-mdpipeline": {
      "command": "uvx",
      "args": [
        "mdpipeline"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add markdown-pipeline-mdpipeline -- uvx mdpipeline
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add markdown-pipeline-mdpipeline --command uvx --arg mdpipeline
```

### Hermes

```yaml
mcp_servers:
  markdown-pipeline-mdpipeline:
    command: "uvx"
    args: ["mdpipeline"]
```

### Netclaw

```json
{
  "McpServers": {
    "markdown-pipeline-mdpipeline": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "mdpipeline"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add markdown-pipeline-mdpipeline -t stdio -c uvx -a mdpipeline
```

### Other

```json
{
  "mcpServers": {
    "markdown-pipeline-mdpipeline": {
      "command": "uvx",
      "args": [
        "mdpipeline"
      ]
    }
  }
}
```

## 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.

### 2026-11-04 (score 53, +1)

No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-03 (score 52, −15)

- [security regression] Malware scan: pass → unverified
- [functional] Package version: 0.1.15 → 0.1.16

### 2026-11-02 (score 67, +1)

No change was recorded against any check on this day. Stability & Change Management went from 0 to 3. That category is still filling its 30-day observation window: 0 days of observed history at the previous scan, 1 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-01 (score 66)

First indexed and scored.

## MCP tools (6)

### `search` (~114 tokens)

Keyword/full-text search over the brain's Markdown (the files its pipelines wrote, plus raw/ and wiki/). Returns ranked files with matching passages and each file's provenance. Covers every pipeline target that has local files: files of other targets have paths like '@pipeline/raw/...' and a 'target' label. Use quotes for an exact phrase. path_prefix (e.g. 'raw/projects/biz') narrows the search.

Input parameters:

- `limit` (integer)
- `path_prefix`
- `query` (string, required)

### `read` (~48 tokens)

Read one Markdown file of the brain (path relative to the brain, e.g. 'raw/projects/biz/pricing.md'). Returns the content and its parsed provenance.

Input parameters:

- `path` (string, required)

### `list` (~46 tokens)

List the folders and Markdown files under path_prefix (default: the top level: the output folders, raw/ and wiki/), with a provenance summary per file.

Input parameters:

- `path_prefix`

### `sync_status` (~53 tokens)

How fresh is the brain? Per pipeline: status, last run (time, result, counts), conflicts, big-change guard state and age since the last successful sync, plus the overall brain age.

Input parameters:

- `pipeline`

### `recent_changes` (~86 tokens)

What changed in the brain's files? The files created, changed or deleted by successful syncs since a time (ISO date or time, default: the last 24 hours), merged per file, with counts. Use it for 'what changed since yesterday?'. pipeline narrows it to one pipeline.

Input parameters:

- `limit` (integer)
- `pipeline`
- `since`

### `sync` (~75 tokens)

Refresh the brain: sync one pipeline (or all pipelines when none is given) from its source folders into the output folder. If the big-change guard blocks the sync, nothing is written and the result is 'blocked': only the owner can approve it in the UI or CLI. This tool cannot approve or force.

Input parameters:

- `pipeline`

## Diagnostics

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

## Score history

- 2026-11-04: 53
- 2026-11-03: 52
- 2026-11-02: 67
- 2026-11-01: 66

## Common questions

### What is the Markdown Pipeline MCP server?

Markdown Pipeline is an MCP server listed in the public MCP registry as io.github.markdown-pipeline/mdpipeline. Your team's Jira as clean Markdown files, kept current for your AI agent. Local and read-only. This page covers its PyPI package (mdpipeline).

### Is the Markdown Pipeline MCP server safe to use?

Markdown Pipeline scores 53 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 4 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 Markdown Pipeline MCP server expose?

Markdown Pipeline exposes 6 tools: search, read, list, sync_status, recent_changes, sync. Their descriptions and schemas cost roughly 422 tokens of context every time the server is loaded.

### Is the Markdown Pipeline MCP server still maintained?

Markdown Pipeline is still listed as active in the MCP registry. We last reached this channel on 4 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 Markdown Pipeline MCP server under?

Markdown Pipeline 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

- PyPI project: https://pypi.org/project/mdpipeline/
- Socket report: https://socket.dev/pypi/package/mdpipeline
- Repository: https://github.com/markdown-pipeline/markdown-pipeline
- Website: https://markdownpipeline.com/?utm_source=mcp-registry&utm_medium=listing
- Changelog RSS feed: https://verifymcp.io/servers/markdown-pipeline-mdpipeline/mdpipeline.xml
- Changelog JSON feed: https://verifymcp.io/servers/markdown-pipeline-mdpipeline/mdpipeline.json
- HTML version of this page: https://verifymcp.io/servers/markdown-pipeline-mdpipeline/mdpipeline