Rokha

Search the Rokha Registry

registry_search

Read-only

Search the public skill and MCP registries at once, plus what builders publish on Rokha (the live count is in GET /api/marketplace/registry/stats), by free-text query. Returns name, slug, provider, author, version, downloads, and description for each match. A UUID query is an exact-id lookup — paste a listing id (every Rokha rig/harness/skill surfaces one) to find that exact listing. Follow up with registry_get_skill to fetch a skill's full SKILL.md and install metadata. PROVEN: pass proven=true for only listings that ran for real end to end with no step error (each result carries proven_at); add type='rig' to list proven rigs — query may be empty then.

Input Schema

Name	Required	Description
`type`	No	Only this listing type, e.g. 'rig'
`limit`	No	Max results (default 10, max 25)
`query`	No	Free-text search, e.g. 'UI design' or 'summarize youtube'
`proven`	No	true = only PROVEN listings (ran for real to a result, no step error)

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedNov 2, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "additionalProperties": true,
+  "type": "object"
+}

Changed3 schema fields changedOct 2, 2026

addedInput schema / properties / proven

Added value: +{
+  "description": "true = only PROVEN listings (ran for real to a result, no step error)",
+  "type": "boolean"
+}

addedInput schema / properties / type

Added value: +{
+  "description": "Only this listing type, e.g. 'rig'",
+  "enum": [
+    "rig",
+    "skill",
+    "mcp",
+    "harness"
+  ],
+  "type": "string"
+}

removedInput schema / required
```
Removed value: -[
-  "query"
-]
```

First observedSep 26, 2026

TDQS

A4.5/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered; the description adds real value beyond that by disclosing the result field set, the exact-id lookup behavior for UUIDs, the meaning of 'proven' (ran end to end with no step error) and the proven_at marker on results. It does not discuss pagination/limit interaction or result ordering, which keeps it short of a 5.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the core purpose and return shape, then the special modes; every sentence carries operational information. The parenthetical 'the live count is in GET /api/marketplace/registry/stats' is incidental noise that an agent calling this tool does not need.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a four-parameter, all-optional read tool with an output schema and clear annotations, the description covers purpose, result fields, the exact-id path, the proven filter, and the natural next call. Nothing an agent needs in order to invoke it correctly is absent.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline would be 3, but the description genuinely adds semantics the schema lacks: a UUID-shaped query is treated as an exact-id lookup rather than text search, and query may be empty when combined with type='rig' plus proven=true. That is meaningful behavioral meaning layered on top of the parameter definitions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource — search the public skill and MCP registries plus Rokha builder listings — by free-text query, and enumerates exactly what comes back (name, slug, provider, author, version, downloads, description). The UUID exact-id lookup mode is called out distinctly, so an agent can tell this apart from a plain keyword search.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives concrete usage routing: follow up with registry_get_skill for full SKILL.md and install metadata, use a UUID query for exact-id lookup, and pass proven=true (optionally with type='rig' and an empty query) to list proven rigs. What's missing is differentiation from the other search siblings in the toolset (market_search, rig_search), so an agent still has to infer which search surface to pick.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Rokha tools Inspect

Try in Browser

Shareable, User-Owned Context BackendPeople, applications, and agents read, write, and coordinate together in one context lake. Reach it over MCP, a CLI, a Python SDK, or REST.fulcradynamics.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.