What an Agent Can Do with Gerolamo MCP

Gerolamo is a technical intelligence platform that scores the open-source landscape across GitHub, arXiv, and Hugging Face on defensibility, frontier risk, and novelty. It exposes that intelligence through a REST API and an MCP server — meaning any MCP-compatible agent can query, analyze, and compose from the corpus directly.

This post walks through what an agent can actually do with the Gerolamo MCP tools, how to connect, and five high-value agent configurations you can run today.

---

1. Discover — "What's out there?"

query_intelligence — Semantic search across all three platforms

A VC analyst's agent asks "what's happening in AI memory systems?" and gets back scored, cross-platform results — repos, papers, and models ranked by relevance.

find_sleepers — Find hidden gems nobody's watching yet

"Find me robotics projects scored 7+ with under 200 stars." Returns repos like a novel SLAM implementation by a solo researcher that's technically excellent but hasn't been discovered.

analyze_competitive_landscape — Map all players in a space

"Show me everything in post-quantum cryptography." Returns 70 entities ranked by velocity — the agent instantly sees who's moving fastest and who's stalling.

---

2. Analyze — "What does it mean?"

get_intelligence_brief — One-call situation report

An agent runs this every morning for "autonomous agents" and gets: 3 new sleepers, the top trending repo (up 400% this week), and the AI-generated narrative summarizing the state of the space.

get_creator_profile — Research a team or person

"Tell me about deepspeedai." Returns all 5 of their projects, average defensibility of 8.2, total traction of 50k+ stars, authority score indicating they're a proven infrastructure builder.

get_creator_network — Map who works with whom

"Who does huggingface collaborate with?" Returns co-created entities and reach — shows the ecosystem around a creator.

find_defensible_clusters — Find groups of related high-value projects

"Show me clusters of score 7+ projects." Returns groups of entities that share creators or technology — reveals hidden ecosystems.

---

3. Fuse — "What should I build or invest in?"

compose_molecules — The power tool. Five modes.

Understand mode — "Take these 4 AI memory projects and explain how they relate." Agent gets individual analysis, relationships, and landscape summary. Useful for research prep.

Augment mode — "I have a chatbot platform. How would these 3 MCP server projects enhance it?" Agent gets prioritized integration recommendations, effort sizing, and a numbered task backlog with acceptance criteria. Feed directly into a project management tool.

Build mode — "Fuse this vector database, this embedding model, and this RAG framework into a new product." Agent gets a SPEC.md with architecture, project structure, tech stack, build phases, and copy-pasteable commands. Paste into Claude Code and start building.

Compare mode — "Should I use FalkorDB or Neo4j for my knowledge graph?" Agent gets head-to-head comparison with clear adopt/watch/skip verdicts and risk factors.

Research mode — "Write an investment thesis on the LLM inference serving space using these 5 sources." Agent gets executive summary, market dynamics, buy/watch/pass on each project, and a strategic thesis. Send to a partner.

---

4. Monitor — "What changed?"

get_my_latest_intelligence — Check subscription alerts

Agent has an alert for "quantum error correction" — checks it daily and surfaces new papers or repos that crossed the score threshold.

search_intelligence — RAG-synthesized answer

"What is the current state of browser automation AI agents?" Gets a synthesized paragraph drawing from multiple sources in the corpus — not just a list of results, but an actual answer.

---

5. Distill & Compose — "Reduce it to reusable parts"

The newer tools operate one level deeper — on the mechanisms inside sources, not just the sources themselves.

distill — Extract reusable patterns from a source

Point it at a source and it pulls out the discrete, reusable mechanisms inside, each stated as a "takes X → produces Y" building block with its provenance. The same mechanism found across many sources collapses into one pattern carrying many provenance links.

search_patterns — Query the pattern library

Search distilled mechanisms by what they do or by effect mode (read, write, external call). Returns the reusable pieces you compose into a capability — not whole projects.

compose_enhancement — Wire patterns into a capability spec

Hand it a set of patterns and a goal, and it composes them into an enhancement spec grounded in real provenance — the pattern-level counterpart to compose_molecules.

submit_meta_molecule / realize_meta_molecule — Author and ground Concepts

submit_meta_molecule creates a Concept: a speculative idea with traced lineage back to the real sources that inspired it. realize_meta_molecule connects that Concept to a real URL once someone builds it.

trace_lineage / find_family — Follow the provenance graph

trace_lineage walks the ancestors or descendants of any source or Concept; find_family returns the full family — ancestors, descendants, and direct edges — in one view.

create_workspace / add_to_workspace / save_composition — Curate and share

Group sources into a named workspace, then persist any composition with save_composition, which gives it a shareable public URL and tracks its full provenance.

suggest_tools / list_workflows / get_workflow / ideate_from_brief — Orchestrate

suggest_tools recommends which tools to chain for a task; list_workflows and get_workflow expose ready-made multi-step prompt templates; ideate_from_brief turns a solicitation or brief into grounded technical approaches drawn from the corpus. And submit_source queues any GitHub repo, arXiv paper, or HuggingFace model for ingestion.

---

Tool Reference

Tool	Returns	Use when
query_intelligence	Scored sources with similarity ranking	"What exists for X?"
find_sleepers	High-score, low-traction sources	"What's under the radar?"
get_intelligence_brief	Sleepers + trending + breakouts + narrative	"What's happening in X this week?"
get_creator_profile	All sources by a creator + stats	"Who is this team?"
compose_molecules (understand)	Technology landscape analysis	"How do these relate?"
compose_molecules (augment)	Integration brief + task backlog	"How do I add these to my project?"
compose_molecules (compose)	SPEC.md with architecture + commands	"Build something new from these"
compose_molecules (compare)	Head-to-head with recommendations	"Which should I adopt?"
compose_molecules (research)	Investment thesis + market analysis	"Should we invest in this space?"
analyze_competitive_landscape	Velocity-ranked entity list	"Who's moving fastest in X?"
get_creator_network	Collaboration graph + reach	"Who works with whom?"
score_stack	Weakest-link defensibility for a stack	"How risky is my dependency set?"
explain_score	Full reasoning behind a score	"Why is this scored this way?"
explore_connections	5-ring intelligence neighborhood	"What surrounds this entity?"
distill	Reusable patterns extracted from a source	"What mechanisms power this?"
search_patterns	Pattern-library matches with provenance	"What building blocks exist for X?"
compose_enhancement	Capability spec wired from patterns	"Compose these mechanisms into a feature"
submit_meta_molecule	A Concept with traced lineage	"Capture a speculative idea"
trace_lineage / find_family	Provenance graph of a source or Concept	"Where did this come from?"
submit_source	Queues a URL for ingestion	"Track this repo, paper, or model"
ideate_from_brief	Grounded approaches from a brief	"Turn this RFP into technical options"

---

Connecting to Gerolamo

Option 1: MCP Server (Claude Code / Cursor / Windsurf)

Add to your Claude Code settings (~/.claude/claude_code_config.json):

{
  "mcpServers": {
    "gerolamo": {
      "type": "sse",
      "url": "https://gerolamo.onrender.com/mcp/sse",
      "headers": {
        "Authorization": "Bearer YOUR_API_KEY"
      }
    }
  }
}

Get your API key at gerolamo.org under Settings > API Keys.

Once connected, Claude Code can use all 31 tools directly in conversation:

• "Search for autonomous drone frameworks scored 7+"
• "Find sleepers in the robotics space"
• "Get the intelligence brief for model context protocol"
• "Compose a Build spec from these entity IDs"

Option 2: REST API (Any Agent)

For custom agents or any HTTP client:

# Semantic search
curl -H "Authorization: Bearer $KEY" \
  "https://gerolamo.onrender.com/api/v1/search?q=autonomous+agents&mode=semantic&limit=10"

# Find sleepers
curl -H "Authorization: Bearer $KEY" \
  "https://gerolamo.onrender.com/api/v1/signals?min_score=7&max_stars=200&limit=10"

# Compose by entity IDs
curl -X POST -H "Authorization: Bearer $KEY" \
  -H "Content-Type: application/json" \
  "https://gerolamo.onrender.com/api/v1/workspace/generate" \
  -d '{
    "mode": "compose",
    "primitives": [...],
    "user_context": "Building a real-time drone coordination platform"
  }'

Compose modes: understand, augment, compose, compare, research

Option 3: CLAUDE.md Integration

For a project that uses Gerolamo as its intelligence source, add to your CLAUDE.md:

## Intelligence Source

This project uses Gerolamo (https://gerolamo.org) for competitive
technical intelligence. The Gerolamo MCP server is connected and
provides these tools:

- `query_intelligence` — search the scored corpus
- `find_sleepers` — discover hidden gems
- `get_intelligence_brief` — daily situation report
- `compose_molecules` — fuse sources into specs
- `distill` / `compose_enhancement` — extract and wire reusable patterns
- `score_stack` — weakest-link defensibility for a dependency set

When researching technologies, libraries, or approaches, query
Gerolamo first to check defensibility scores, threat profiles,
and competitive positioning before making architecture decisions.

---

Five Agent Configurations

The Morning Scout

Every morning, run get_intelligence_brief for your 5 key topics. If any sleepers or breakouts appear, run compose_molecules in Research mode on them. Email the result to your team.

The Competitive Tracker

For each company in your portfolio, run get_creator_profile weekly. Track their source count, average score, and velocity over time. Alert if a competitor's output accelerates.

The Build Agent

Search for a capability you need. Find the top 3-5 sources. Compose in Build mode. Pass the SPEC.md to Claude Code. Start implementation. Discovery to code in one pipeline.

The Due Diligence Agent

For an acquisition target, run get_creator_profile + compose_molecules in Compare mode against competitors. Get a Research brief on the market. All data-driven, all from the corpus.

The Alpha Hunter

Run find_sleepers daily with min_score=7, max_traction=100. These are the highest-signal, lowest-visibility sources in the entire corpus. The repos that are about to break out but haven't yet. Track them in bookmarks and check get_intelligence_brief for breakout detection.

---

Own your intelligence. Build with certainty.

• Explore Gerolamo: gerolamo.org
• Connect your agents: Product page
• Request a consultation: Get started