Robot directory for AI agents: 830+ robots, 290+ brands, 1,000+ datasets, 260+ professions scored.
Scored across 10 tools
Most tools map cleanly to a resource+action (search_robots/get_robot, search_datasets/get_dataset, search_suppliers/get_supplier), so misselection risk is low. The one weak pair is get_category vs get_component_category, which share vocabulary and could be confused without reading the descriptions, and compare_robots/get_job_automation_risk are singletons that don't fit the search/get rhythm.
All ten tools follow a strict verb_noun snake_case pattern (search_*, get_*, compare_*), with no camelCase or verb-style mixing. Names are predictable enough that an agent can guess the shape of a tool before reading its description.
Ten tools for a read-only directory spanning four sub-domains (robots, categories, datasets, suppliers) plus one scoring endpoint is well-scoped. Each tool earns its place and nothing appears redundant or missing at the count level.
Robots, datasets, and suppliers each get a full search+get pair, which covers the core lookup workflows. Gaps: get_job_automation_risk is a dead end with no way to browse or list professions, and brand is a documented filter for search_robots but has no entity lookup, nor is there a way to enumerate categories.
Compare two robots side by side on specs, price, and capabilities. Returns a comparison URL and key differences.
Inputs: robot_a (required), robot_b (required).
Get all robots in a specific category with specs and prices. Returns the full list of active robots in that category from the Geppetto directory.
Inputs: category_slug (required).
Get a robot hardware component category (a 'part' type) by slug, with its supply-chain analysis and full supplier list: bottleneck risk, China concentration, supplier counts, and each supplier.
Inputs: category_slug (required).
Get the full record for a specific robot training dataset by slug: specs, license, access type, collection method, citation, and source links.
Inputs: slug (required).
Get the Geppetto Robot Impact Score (0-100) for any profession. Composite of task-automation research (35%, the Oxford Frey and Osborne score), IFR robot deployment (30%), an academic-consensus score (20%, the average of the Oxford score and the OECD risk band), and robot density (15%). The O*NET-SOC code is a cross-reference only, not a scoring input. Higher means more automation pressure on the occupation.
Inputs: profession_slug (required).
Get full specs and details for a specific robot by its slug. Returns all specifications, price, brand, description, features, and direct URL.
Inputs: slug (required).
Get the full record for a specific robot hardware supplier by slug: components supplied, OEM relationships, country, public-listing and stock code, bottleneck risk, and sources.
Inputs: slug (required).
Search Geppetto's directory of 1,000+ robot training datasets by platform, modality, license, or commercial-use. Returns name, slug, platforms, sensor modalities, episode count, hours, license, access type, and URL.
Inputs: query, license, category, modality, +2 more.
Search Geppetto's directory of 830+ robots by category, brand, price range, or use case. Returns robot name, slug, category, brand, price range, and key specs.
Inputs: query, category, maxPrice.
Search Geppetto's directory of 140+ robot hardware component suppliers by component category, country, or keyword. Returns name, slug, component category, country, public-listing/stock code, and bottleneck risk.
Inputs: query, country, component.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Vendor-neutral catalog of 300+ commercial robots: search, compare specs, request vendor intros.
AI Agent Source Registry. 288K+ curated sources for agentic search and discovery.
Evidence-based humanoid robot data: RadarScore ratings, evidence grades A-D, prices, EU availability
Sourced, dated data on consumer robots and physical AI: specs, prices, availability, evidence.
Add one secure layer between your agents and this server.
