Self-hosted documentation crawler and Markdown MCP server that lets Claude query crawled technical documentation, list files, read sections, search content, inspect metadata, and keep generated Markdown in sync.
Open the source and read safety notes before installing.
Source-backed facts for citing this resource, derived directly from the registry — also available as plain text for AI assistants.
Decision playbook
Signals are present but mixed. Use the checklist below to confirm the source and operational safety for your environment.
0
63
—
No baseline selected
No major trust-signal divergence detected in the current selection.
Confirm ownership and provenance before trusting install instructions.
Source link availableRequired
Open the canonical repository and verify ownership.
Source provenance statusRequired
Marked as source-backed.
Metadata reviewed
No reviewed flag detected in metadata.
Validate risk disclosures before installation or API wiring.
Safety notes presentRequired
Review the listed safety guidance before running commands.
Privacy notes presentRequired
Review data handling notes before connecting accounts or secrets.
Trust level risk gateRequired
Trust level does not block evaluation.
Check package metadata and artifact integrity signals.
Install payload available
Install or copy payload is available for review.
Package verification flag
No package verification flag provided.
Checksum metadata
No checksum provided for downloaded artifact.
Use compare context to validate trade-offs before adoption.
Compare tray has multiple entries
Add at least one more entry to compare trust differences.
Baseline comparison available
No baseline peer selected yet.
Diverging trust signals identified
No major trust-signal divergence found.
Setup at a glance
Copy-ready — paste the snippet to get started.
Adoption plan
Current risk score 24/100. Use staged verification before broader rollout.
Validate source and review signals before any execution.
Confirm source provenanceRequired
Source URL/provenance metadata is present.
Confirm metadata review state
No review metadata found; increase manual validation.
Verify install payload
Install/config payload exists and can be inspected.
Confirm safety, privacy, and package integrity signals.
Review safety notesRequired
Safety notes are present.
Review privacy notesRequired
Privacy notes are present.
Verify package integrity metadata
No package verification/checksum metadata.
Adopt in controlled steps based on the selected plan.
Run in isolated sandbox firstRequired
Use a constrained sandbox and observe behavior across multiple tasks.
Roll out graduallyRequired
Roll out to a small cohort before wider usage.
Set monitoring and fallback
Define rollback path and monitor errors after adoption.
Evidence readiness
Missing required evidence: Metadata review. Risk score 31.
Source repository/provenance is listed.
Required in this preset
Review metadata is missing.
Required in this preset
Safety notes are present.
Required in this preset
Privacy notes are present.
Optional in this preset
Package integrity metadata is missing.
Optional in this preset
Install payload is available.
Required in this preset
Required gaps: Metadata review
Decision timeline
Blocking gaps: Check metadata review status. Risk 28.
triage
Source/provenance metadata is available.
triage
Review metadata is missing.
verify
Safety notes are available.
verify
Privacy notes are available.
verify
Package integrity metadata is missing.
rollout
Install payload is available.
Blockers: Check metadata review status
Prerequisite readiness
5 prerequisites to line up before setup. Includes a review or approval gate.
Safety & privacy surface
5 safety and 5 privacy notes across 5 risk areas. Review closely: credentials & tokens, network access, third-party handling.
Disclosure: Apache-2.0-licensed open-source project. The entry focuses on the repository's Docker-backed Fast Markdown MCP server and documentation-crawling workflow.
{
"mcpServers": {
"fast-markdown": {
"command": "docker",
"args": [
"exec",
"-i",
"devdocs-mcp",
"python",
"-m",
"fast_markdown_mcp.server",
"/app/storage/markdown"
]
}
}
}DevDocs combines a documentation crawler, a local web UI, and a Docker-backed Fast Markdown MCP server. The crawler writes documentation into local Markdown and metadata files, while the MCP server exposes those files to Claude through tools for listing files, reading Markdown, searching content, finding tagged documents, inspecting sections, and getting document statistics.
Use it when you want Claude to work from a private or self-hosted copy of
technical documentation instead of repeatedly searching the live web. The
upstream Docker setup runs the MCP process over stdin/stdout through
docker exec -i, so the client communicates with the devdocs-mcp container
rather than a public network endpoint.
These sources were reviewed on 2026-06-06 at commit
9845479d0aeb7523abaab85723d0dfcf832fe1d3. Use the pinned commit for the
Docker startup script and MCP setup reviewed here; inspect upstream changes
before running newer branch tips.
Clone the repository, check out the reviewed commit, and start the Docker stack using the pinned upstream scripts:
git clone https://github.com/cyberagiinc/DevDocs.git
cd DevDocs
git checkout 9845479d0aeb7523abaab85723d0dfcf832fe1d3
./docker-start.sh
Connect Claude or another MCP client to the containerized MCP process:
{
"mcpServers": {
"fast-markdown": {
"command": "docker",
"args": [
"exec",
"-i",
"devdocs-mcp",
"python",
"-m",
"fast_markdown_mcp.server",
"/app/storage/markdown"
]
}
}
}
Restart the MCP client after changing its server configuration. Keep the generated Markdown storage mounted only where DevDocs and the approved MCP client need access.
DevDocs can crawl websites and convert them into model-visible local Markdown. Before crawling, confirm that the target permits automated access and that the depth, concurrency, and selected URLs are appropriate. Avoid crawling customer portals, authenticated pages, or internal knowledge bases unless you have explicit approval and a retention plan.
The MCP server exposes generated Markdown files, metadata, sections, tags,
search snippets, and document statistics to the connected model provider. Treat
the storage, logs, and crawl_results directories as sensitive. Replace
the default Crawl4AI demo token before shared use, avoid exposing local service
ports on untrusted networks, and keep optional LLM provider API keys out of
logs, shell history, screenshots, and repository files.
No cyberagiinc/DevDocs, DevDocs MCP Server, Fast Markdown MCP from DevDocs,
or matching source URL entry was found in content/mcp or README.md.
Show that DevDocs MCP Server is listed on HeyClaude. Paste this Markdown into your README — it renders the badge and links back to this page.
[](https://heyclau.de/entry/mcp/devdocs-mcp-server)DevDocs MCP Server side by side with 3 alternatives on trust, install, platform support, and disclosed safety notes — all from reviewed registry metadata.
| Field | Self-hosted documentation crawler and Markdown MCP server that lets Claude query crawled technical documentation, list files, read sections, search content, inspect metadata, and keep generated Markdown in sync. Open dossier | Official Agentset MCP server that lets Claude retrieve cited knowledge-base results from an Agentset namespace through the `knowledge-base-retrieve` tool, with optional tenant scoping and custom tool descriptions. Open dossier | Local-first codebase intelligence MCP server that indexes repositories with tree-sitter, stores searchable chunks in DuckDB, and gives Claude semantic search, regex search, daemon status, and deep code research tools. Open dossier | Code intelligence MCP server with a Zig core for local project indexing, structural outlines, symbol lookup, search, dependency graphs, snapshots, remote public-repo queries, and fallback edits. Open dossier |
|---|---|---|---|---|
| Next steps | ||||
| Trust | ||||
| Review status | Not reviewed | Not reviewed | Not reviewed | Not reviewed |
| Package trust | Package not verified | Package not verified | Package not verified | Package not verified |
| Source provenance | Source-backed | Source-backed | Source-backed | Source-backed |
| Submitter | oktofeesh1 | oktofeesh1 | oktofeesh1 | oktofeesh1 |
| Install risk | Review first | Review first | Review first | Review first |
| Notes | Safety ✓ Privacy ✓ | Safety ✓ Privacy ✓ | Safety ✓ Privacy ✓ | Safety ✓ Privacy ✓ |
| Brand | — | |||
| Category | mcp | mcp | mcp | mcp |
| Source | Source-backed | Source-backed | Source-backed | Source-backed |
| Author | CyberAGI | Agentset | ChunkHound | justrach |
| Added | 2026-06-06 | 2026-06-06 | 2026-06-06 | 2026-06-06 |
| Platforms | ||||
| Harness | ||||
| Source repo | — | — | — | — |
| Safety notes | ✓DevDocs runs a multi-container Docker stack with frontend, backend, MCP, and Crawl4AI services; use the reviewed commit below instead of executing a moving branch tip. The crawler can fetch and process external websites, so review crawl targets, rate limits, robots rules, and site terms before crawling. The backend and crawler use a Crawl4AI API token; replace the demo token before shared or production use. The MCP container mounts generated Markdown and logs, and its tools can read, search, sync, and expose that content to the MCP client. Local services are exposed on development ports by the Docker stack; do not expose them on untrusted networks without authentication and network controls. | ✓The MCP server sends Claude's retrieval queries to the Agentset API using the configured API key and namespace. The `knowledge-base-retrieve` tool can return up to 100 results per call and can rerank results by relevance. Namespace and tenant selection control which indexed documents are searchable; review them before connecting a shared agent. API keys should be scoped, rotated, and stored only in the MCP server environment or a secret manager. Custom tool descriptions can influence when the model calls the retrieval tool, so review them before use in production workflows. | ✓ChunkHound reads source files, Markdown, text, PDFs, and supported config files under the target directory and stores indexed chunks in a local database. Realtime indexing and daemon mode can continue watching project files after the initial MCP connection. Code research and web search tools require embedding, reranking, and LLM configuration and may invoke local CLIs or external model APIs depending on settings. Exclude generated files, vendored dependencies, secrets, large artifacts, and unrelated repositories before indexing broad workspace roots. Review MCP client configuration carefully when using an absolute project path in a global Claude Desktop config. | ✓CodeDB indexes local projects and exposes file tree, outline, search, symbol, caller, dependency, read, snapshot, project, and context tools to the MCP client. CodeDB's `codedb_edit` tool exists as a fallback editing tool and can create, replace, insert, delete, or modify files when used by a client without native edit tooling. The npm package runs a postinstall step that downloads a native binary from GitHub Releases; review package and release provenance in environments that restrict native binaries. Remote repo queries use the public `api.wiki.codes` service and should be treated as network access outside the local repository. The upstream README marks the project as alpha software, with parser coverage and snapshot formats still stabilizing. |
| Privacy notes | ✓Crawled pages, generated Markdown, JSON metadata, source URLs, tags, search queries, local logs, and MCP tool outputs may contain proprietary documentation, customer data, internal architecture, or third-party website content. The Markdown MCP server can reveal full document text, section contents, table of contents, metadata, and search snippets to the connected model provider. Logs, crawl results, mounted volumes, and container transcripts can retain documentation-derived content after an MCP session ends. Optional LLM-related Crawl4AI environment variables can route documentation-derived content to external model providers if configured. Keep storage directories, crawl outputs, API tokens, and generated documentation artifacts out of public repositories unless publication is explicitly approved. | ✓Retrieved chunks can include private documents, product specs, policies, support content, internal procedures, historical project information, or customer-specific data. Retrieval queries, namespace IDs, tenant IDs, document chunks, citations, and tool outputs may be visible to the MCP client, model provider, Agentset logs, and application telemetry. Tenant IDs are useful for data segregation, but incorrect tenant or namespace configuration can expose the wrong knowledge base. Do not paste API keys, namespace IDs, tenant IDs, or retrieved private chunks into shared issue reports, screenshots, or repository files. | ✓Indexed chunks, file paths, symbols, comments, Markdown, PDFs, configuration values, database files, daemon state, and search results can reveal proprietary source code and internal architecture. Embedding, reranking, LLM, and web search providers may receive code-derived queries or snippets if configured. Local ChunkHound database files, logs, daemon state, and MCP transcripts may retain code-derived context after the session ends. Avoid sharing ChunkHound databases, config files with API keys, verbose logs, research outputs, and screenshots from private repositories. | ✓Local indexes, snapshots, file trees, symbol names, dependency graphs, snippets, read results, and search results can reveal proprietary code structure and implementation details. Upstream documents sensitive-file blocking for patterns such as environment files, credentials, and keys, but users should still review ignore rules and avoid indexing secret-heavy directories. CodeDB writes telemetry to `~/.codedb/telemetry.ndjson` unless `CODEDB_NO_TELEMETRY=1` is set, then syncs aggregate tool counts, latency, startup, file count, line count, language, version, and platform data on MCP session close. Upstream telemetry docs state that source code, file contents, file paths, and search queries are not collected. Remote public-repo queries and local MCP responses may still be logged by MCP clients, model providers, and terminal history. |
| Prerequisites |
|
|
|
|
| Install | | | | |
| Config | | | | |
| Citations | ||||
| Claim | Unclaimed | Unclaimed | Unclaimed | Unclaimed |
Query Agentset RAG namespaces from Claude through the official `@agentset/mcp` server.
Run `chunkhound mcp` to give Claude local semantic and regex code search with optional LLM-backed research over indexed repositories.
Source-backed guides for putting this to work.
Write a claude-code-hint tag to stderr under CLAUDECODE, and Claude Code prompts users once to install your official-marketplace plugin.
Loading live community signals…
A short, calm digest of reviewed Claude resources. Unsubscribe any time.