DocFlow MCP Server
Allows automated branch creation, committing, pushing, and opening Pull Requests on Bitbucket for documentation updates.
Allows automated branch creation, committing, pushing, and opening Pull Requests on GitHub for documentation updates.
Allows automated branch creation, committing, pushing, and opening Merge Requests on GitLab for documentation updates.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@DocFlow MCP ServerSearch docs for how authentication works"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
DocFlow ๐
Agent-Powered, LLM-Optimized Documentation Generation & MCP Serving System
DocFlow automatically generates, updates, and serves dual-audience documentation (rich Markdown for humans + high-density JSON for LLMs) from Git repository activity.
Unlike traditional doc tools that rely on direct LLM API keys or lock you into specific vendors, DocFlow generates minimal, focused "caveman prompts" that can be executed by any coding agent (Antigravity, Cursor, Claude Code, Cline, Codex, Hermes, Continue, etc.) within your organization's approved toolset.
๐ Key Features
๐ 1 App Repo : 1 Doc Repo Model: Strict 1-to-1 pairing between an application source repository (or monorepo root) and its dedicated documentation repository.
๐๏ธ Infrastructure First: Automatically scans and documents system architecture, frameworks, and hosting environments (Dev/Staging/Prod) before chunking feature modules.
๐ค Agent Agnostic: Zero LLM API key dependencies. Generates structured task prompts in
prompts/pending/for any agent to execute.๐ Dual-Audience Output: Maintains human-readable
index.mdand token-optimizedcontext.jsonfor every feature module.๐ MCP Server Included: Built-in FastMCP server serving documentation tools (
search_docs,get_feature,get_wip,get_full_context) overstdioandsse.๐ Decoupled Doc Repo: Keeps documentation in a separate, dedicated repository to keep application source repositories clean.
๐ Work-In-Progress Tracking: Scans active feature branches and updates
status/wip.md&status/wip.json.๐ Standard Specification Support: Automatically generates
llms.txtandllms-full.txtdiscovery files.๐ Multi-Platform MR/PR Creation: Automated branch creation, committing, pushing, and Pull/Merge Request opening for GitHub, GitLab, and Bitbucket.
Related MCP server: mcp-docs
๐ Architecture & Workflow
App Repo (Merge/Release) โโโ DocFlow Git Analyzer
โ
โผ
Prompt Builder (Jinja2)
โ
Caveman Task Prompt
โ
โผ
Agent Runner (shell / manual)
โ
โผ
Target Docs Repository
โโโ architecture/ (Hosting & Frameworks) [Init First]
โโโ features/<feature>/
โ โโโ index.md (Human)
โ โโโ context.json (LLM)
โโโ status/ (wip.md, wip.json)
โโโ prompts/ (pending/ & completed/)
โโโ llms.txt & llms-full.txt
โโโ CONVENTIONS.md
โ
โผ
Doc Branch & MR Creator
โ
โผ
FastMCP Server
(stdio / SSE transports)โก Quick Start
Installation
# Clone the repository
git clone https://github.com/YOUR_USERNAME/docflow2.git
cd docflow2
# Create a virtual environment (recommended for Linux/PEP 668)
python3 -m venv --without-pip .venv
curl -sS https://bootstrap.pypa.io/get-pip.py | .venv/bin/python3
# Install DocFlow in editable mode
.venv/bin/pip install -e .
# Activate the virtual environment
source .venv/bin/activateBasic Commands
# 1. Initialize documentation for an application repository
docflow init --repo /path/to/app-repo --docs /path/to/docs-repo --mode manual
# 2. Track active feature branches & work-in-progress
docflow status --repo /path/to/app-repo --docs /path/to/docs-repo
# 3. Generate documentation update prompts from git diffs
docflow generate --repo /path/to/app-repo --docs /path/to/docs-repo --from main~1 --to main
# 4. Commit doc updates, push branch, and create Pull Request
docflow publish --docs /path/to/docs-repo --platform github
# 5. Start the MCP Server for LLM agent integration
docflow serve --docs /path/to/docs-repo --mode stdio๐ Documentation Repository Layout
docs-repo/
โโโ CONVENTIONS.md # Documentation format standards
โโโ llms.txt # Discovery index
โโโ llms-full.txt # Concatenated context file
โ
โโโ architecture/ # Baseline architecture & infrastructure
โ โโโ index.md # Frameworks, Dev/Staging/Prod envs
โ โโโ context.json # Compact LLM metadata
โ
โโโ features/ # Feature-based documentation
โ โโโ authentication/
โ โ โโโ index.md # Detailed human docs
โ โ โโโ context.json # Compact LLM JSON
โ โ โโโ files.md # File manifest
โ โ โโโ changelog.md # Historical change log
โ โโโ ...
โ
โโโ status/ # Work-in-progress active branch docs
โ โโโ wip.md
โ โโโ wip.json
โ
โโโ prompts/ # Task prompt repository
โโโ pending/ # Prompts waiting for agent execution
โโโ completed/ # Completed task prompts (audit log)โ๏ธ Configuration (.docflow.yml)
Place .docflow.yml in your application repository root or documentation repository root:
project:
name: "MyApplication"
app:
repo_path: "/path/to/app-repo"
docs:
repo_path: "/path/to/docs-repo"
agent:
mode: "shell" # "shell" (automatic CLI agent execution) or "manual" (stage prompts in prompts/pending/)
command: "agy --dangerously-skip-permissions --add-dir {docs_repo} -p \"$(cat {prompt_file})\""
platform:
type: "github" # github | gitlab | bitbucket | generic
auto_mr: true
generation:
full_diff_threshold: 200
ignore:
- "*.lock"
- "node_modules/"
- "dist/"
- "__pycache__/"Agent Execution Modes
Shell Mode (
mode: shell): DocFlow invokes your CLI coding agent (e.g.,agy,opencode,claude) to execute task prompts immediately. The agent writes files directly into target paths in your documentation repository, and DocFlow moves executed prompts fromprompts/pending/toprompts/completed/.Manual Mode (
mode: manual): DocFlow generates prompts insideprompts/pending/. Each prompt includes an explicitCRITICAL OUTPUT FILE LOCATION DIRECTIVEwith exact target absolute paths so that external agents write files directly into the target docs repository.
๐ Configuration Dashboard (docflow info)
View repository pairing, agent settings, documented feature modules, and pending task prompts at any time:
docflow infoOutput:
DocFlow Information Dashboard
Project Name: MyApplication
App Repo: /path/to/app-repo (exists)
Docs Repo: /path/to/docs-repo (exists)
Agent Mode: shell (agy --dangerously-skip-permissions --add-dir {docs_repo} -p "$(cat {prompt_file})")
Platform: github
Documented Features (7): config, core, components, scripts, public, pages, lib
Pending Prompts (0): None๐งช Testing
Run the full pytest suite:
pytest -v๐ License
This project is licensed under the MIT License.
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- AlicenseBqualityDmaintenanceA Model Context Protocol server that enables AI agents to access, search, and understand structured package documentation and source code from Git repositories. It automatically generates specialized tools to browse module overviews, components, and detailed documentation for technical libraries.14287MIT
- Alicense-qualityDmaintenanceGeneric MCP server that exposes Markdown documentation to LLMs, enabling them to search and answer questions about any software documentation.MIT
- Alicense-qualityAmaintenanceLocal-first MCP server for querying multi-repo engineering documentation artifacts from a SQLite corpus.391AGPL 3.0
- Alicense-qualityAmaintenanceMCP server that fetches documentation from public git repositories at specific versions, enabling AI coding assistants to access up-to-date, ref-pinned docs from source repos.72Apache 2.0
Related MCP Connectors
Turn a GitHub repo or docs site into agent-ready context: pack it or search it, over MCP.
MCP server for AgentDocs (agentdocs.eu): read, search, write, comment on & share Markdown docs.
Agent-native MCP server over the public saagarpatel.dev corpus. Read-only, stateless.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/debjit/docflow'
If you have feedback or need assistance with the MCP directory API, please join our Discord server