Click on "Deploy 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., "@Hermes Atlas MCP Server search for memory persistence tools"
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.
MCP server for the Hermes Atlas ecosystem directory — gives AI agents instant access to 169+ quality-filtered tools, skills, plugins, and integrations for Hermes Agent.
Hermes Agent has a massive and growing ecosystem. This MCP server turns that ecosystem into instant expandability — agents can discover, compare, and recommend tools without leaving their conversation.
Related MCP server: Sylex Search
Add to your MCP client config:
{
"mcpServers": {
"hermes-atlas": {
"command": "npx",
"args": ["hermes-atlas-mcp"]
}
}
}Or with Docker/stdio:
{
"mcpServers": {
"hermes-atlas": {
"command": "node",
"args": ["/path/to/hermes-atlas-mcp/dist/index.js"]
}
}
}Tool | Description | Example |
| Full-text search across 169 repos |
|
| Browse 12 ecosystem categories |
|
| Detailed repo info + AI summary |
|
| Match tools to your use case |
|
| Trending/rising repos this week |
|
| Curated lists overview |
|
| Specific curated list with per-repo descriptions |
|
| Aggregate stats, category breakdown, latest version |
|
| RAG over research knowledge base (requires embeddings) |
|
The ask_atlas tool provides RAG-powered answers grounded in 27 research files (6,500+ chunks) covering Hermes Agent installation, architecture, skills system, deployment, and best practices.
Install the embeddings (~70MB) separately:
npx hermes-atlas-mcp install-embeddings
# or equivalently:
npx hermes-atlas-installThe server auto-detects the embeddings at startup and adds the ask_atlas tool when available. Without embeddings, all other tools work perfectly using the summaries index.
┌────────────────────────────────────────────┐
│ hermes-atlas-mcp │
│ │
│ ┌──────────┐ ┌──────────────┐ │
│ │ repos │ │ summaries │ │
│ │ (169) │ │ (AI-generated│ ← bundled │
│ └────┬─────┘ │ per-repo) │ or fetched│
│ │ └──────────────┘ │
│ ┌────┴──────────────────────┐ │
│ │ lists, featured, stats │ ← cached │
│ └───────────────────────────┘ (4hr TTL) │
│ │
│ ┌───────────────────────────┐ optional │
│ │ chunks.json (70MB) │ ← install │
│ │ RAG knowledge base │ separately│
│ └───────────────────────────┘ │
└────────────────────────────────────────────┘
│
stdio (MCP)Zero-config: Works immediately with no API keys needed
Offline-capable: Bundled data works without network; fresh data fetched in background
Light: Core data is ~300KB; embeddings are opt-in at 70MB
Fast: Full-text search and recommendations complete in <50ms
All data sourced from ksimback/hermes-ecosystem — a community-curated directory security-reviewed before inclusion.
File | Size | Content |
| 60KB | 169 repos — owner, name, description, stars, category, official flag |
| 189KB | AI-generated summaries + highlights per repo |
| 2KB | 6 curated lists (best memory, top skills, deployment, etc.) |
| 26KB | Per-repo descriptions within each curated list |
| 241B | Currently featured/trending repos |
| 374B | Latest Hermes Agent version |
| 70MB | 6,554 research chunks with pre-computed embeddings (optional) |
git clone https://github.com/your-user/hermes-atlas-mcp.git
cd hermes-atlas-mcp
npm install
npm run build
# Test interactively
echo '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2024-11-05","capabilities":{},"clientInfo":{"name":"test","version":"0.1"}}}' | npm start
# Watch mode
npm run devMIT. Data sourced from hermes-ecosystem (MIT/CC BY 4.0).
Get aggregate ecosystem statistics — total repos, total stars, category breakdown, latest Hermes version.
Inputs: no named parameters.
Get currently featured/trending repos in the Hermes ecosystem — the best new additions and rising projects.
Inputs: no named parameters.
Get a specific curated list with per-repo descriptions and recommendations.
Inputs: slug (required).
Get curated lists (best memory providers, top skills, deployment options, etc.). Each list has a title, description, and per-repo descriptions.
Inputs: no named parameters.
Get detailed information about a specific repo including its AI-generated summary, highlights, and category. Use owner/repo format (e.g. 'NousResearch/hermes-agent').
Inputs: slug (required).
List all ecosystem categories with repo counts. Useful for discovering what types of tools exist in the Hermes ecosystem.
Inputs: no named parameters.
Get personalized recommendations for Hermes ecosystem tools based on a use case description. Matches repos using AI-generated summaries and highlights. Great for answering 'what should I use for X?' questions.
Inputs: use_case (required), limit.
Search the Hermes Atlas ecosystem for repos matching a query. Searches across repo names, descriptions, categories, and owners. Returns ranked results with star counts and official badges.
Inputs: query (required), category, official_only, limit.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 8 tools
Each tool targets a distinct function: stats, featured repos, curated lists, single repo details, categories, personalized recommendations, and search. No two tools have overlapping purposes, minimizing agent confusion.
Most tools follow a verb_noun pattern with underscores (get_featured, get_list, search_repos), but ecosystem_stats uses noun_verb and recommend lacks an underscore, creating mild inconsistency.
Eight tools are appropriate for an ecosystem explorer, covering search, browsing, recommendations, and stats without being overwhelming or sparse.
The set covers key exploration tasks: searching, filtering by category or list, getting details, and recommendations. Missing is a bulk listing of all repos, but search_repos can substitute, so only minor gaps.
Search a curated directory of agent tools, MCP servers, APIs, protocols and skills. No auth.
Discovery for the agent ecosystem: findable businesses, tools, knowledge, agent spaces, skills.
Directory of APIs, merchants, and tools AI agents can actually use.
Discover, inspect and run 63,000+ agent tools from one balance. Pay per call, no subscriptions.