Skip to content
Agentmart
Submit a tool

ExpertPack MCP

Serve ExpertPack knowledge packs over MCP with hybrid search, graph traversal and provenance.

Connector by brianhearn · GitHub account verified by the MCP Registry

IndexedLicense unknownLocal (stdio)★ 1
Write a review

Chalk Labs

Need help deploying ExpertPack MCP?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Codex, VS Code, Cursor, Windsurf, Claude Desktop. Read the repository before you give any tool access to your data.

npx agentmarket install connector/brianhearn-ep-mcp

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Serve ExpertPack knowledge packs over MCP with hybrid search, graph traversal and provenance.

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this server can do and what it asks for, from its tool list, install config and code. Checked Oct 25, 2026.

Tools
4 read · 0 write · 0 deleteRead-only
Secrets
2 (API keys, tokens or passwords)
Install scripts
None found
Runs as
Python package

Tools by what they do 4

Read from the source code; the running server may list different tools.

Read 4 · Look things up without changing anything.

  • ep_graph_traverse_tool
  • ep_list_topics_tool
  • ep_read_tool
  • ep_search_tool

Secrets and settings it asks for

Secrets: values you paste in that let it act as you.

  • AZURE_OPENAI_API_KEY
  • GEMINI_API_KEY

Network hosts it talks to 4

  • claude.ai · found in code
  • expertpack.ai · found in code
  • github.com · found in code
  • glama.ai · found in code

Files it touches

  • Any path the agent passes to its tools

Tools (4)

Read from the source code; the running server may differ. Descriptions are the server’s own words; hidden characters are shown as [U+…].

  • ep_graph_traverse_toolTraverse ExpertPack Graphread-only

    Traverse the ExpertPack knowledge graph from a starting file. Explores connections between content files (concepts, workflows, references, etc.) through the pack's knowledge graph. Args: file_path: Starting file path (e.g. 'concepts/auto-build.md'). depth: Number of hops to follow (1-3, default 1). edge_kinds: Filter by edge types (wikilink, related, context). If omitted, follows all edge types. Returns: Start node info, connected nodes, and traversal stats.

  • ep_list_topics_toolList ExpertPack Topicsread-only

    List available topics and content structure in the ExpertPack. Args: type: Filter by content type. If omitted, returns all types. Returns: Pack metadata and grouped file listing.

  • ep_read_toolRead ExpertPack Fileread-only

    Read a whole ExpertPack atom by path or provenance id. Search hits are locators. Call this after ep_search to load the complete atom (opening paragraph plus body), not a sidecar fragment. Args: path: Pack-relative file path (e.g. 'concepts/routing.md'). id: Provenance id (e.g. 'my-pack/concepts/routing'). reconstruct: Include original markdown and provenance block. section: Optional section slug or heading text (from ep_search heading_path / ep_read sections) to read just that section. neighbors: With section, also return previous/next sections. Returns: Full…

  • ep_search_toolSearch ExpertPackread-only

    Search the ExpertPack for relevant domain expertise. Args: query: Natural language search query. type: Filter by content type (concept, workflow, reference, troubleshooting, faq, specification, etc.) tags: Filter by content tags. Results must match at least one. max_results: Maximum results to return (1-50, default 10). reconstruct: Include original markdown spans and provenance blocks for verification/reconstruction (default false). Returns: Ranked results with provenance metadata.

Signals

Stars
1
Forks
1
Open issues
0
Weekly downloads
154
Last commit
Oct 20, 2026 (17 days ago)
Last release
Oct 20, 2026 (17 days ago)
Last package publish
Oct 20, 2026 (17 days ago)

From GitHub (fetched Oct 24, 2026) and the package registry.

Details

Registry name
io.github.brianhearn/ep-mcp
Version
0.7.0
Auth
API key
Packages
pypi ep-mcp
License
License unknown
Repository
github.com/brianhearn/ep-mcp
Website
expertpack.ai
First seen
Oct 24, 2026
Last checked
Nov 1, 2026
Source
Official MCP Registrygithub-graphql

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get ExpertPack MCP running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying ExpertPack MCP?

CallGet help
Cite this page

ExpertPack MCP. Agent Mart. https://agentmart.dev/connectors/brianhearn-ep-mcp (last updated 2026-11-01)