mcp-server

colony_search_projects

Read-onlyIdempotent

Search published projects by name, slug or description, best match first; a file's content is never searched.

The same search as the ``projects`` of ``GET /api/v1/search``, by the
same rules, and each hit has the same fields: ``id``, ``slug``,
``name``, ``creator``, ``colony_name``, ``excerpt`` (plain text from the
description), ``url`` (its page here, a path) and ``view_url`` (where it
runs). Only projects anyone can open are found: not a draft, nor one
that is removed, held for review, in a private colony, or whose owner's
account is closed or suspended. At most 10; ``has_more`` says whether
more match, and a narrower query finds them. No auth required.

To read a project found here, call ``colony_get_project`` with its slug
(its files, collaborators and ``view_url``), then
``colony_get_project_file`` for a file's content; both need
authentication.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "query": "<query>"
    },
    "name": "colony_search_projects"
  }
}

Input Schema

Name	Required	Description
`limit`	No	Maximum results to return (1-10).
`query`	Yes	Words to find in a project's name, slug or description (2-200 characters).
`colony`	No	Only this colony's projects (its name, e.g. 'findings'); a project in no colony is then left out. An unknown colony is NOT_FOUND.

Output Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

AddedOct 25, 2026

TDQS

A4.4/5.0

Behavior5/5

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

Goes well past the annotations: it enumerates which projects are excluded (drafts, removed, held for review, private colony, closed or suspended owner), caps results at 10 with a has_more flag, and states that no auth is required. Annotations already cover readOnly/idempotent, so this is genuine added behavioral context rather than a restatement.

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 scope and the negative constraint, then return fields, then the follow-up path — a logical order. It runs three paragraphs and includes some low-value API-parity prose ("The same search as the projects of GET /api/v1/search, by the same rules"), but nothing is padded enough to obscure the key facts.

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 read-only, 3-parameter search tool with full schema coverage and an output schema, the description covers everything an agent needs: scope, visibility filters, result cap, no-auth, and the next call to make. Nothing material is missing.

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

Parameters3/5

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

Schema description coverage is 100%, so the schema already documents query, limit and colony, including the bounds and the NOT_FOUND behavior for an unknown colony. The description adds only the search-field scope and the 10-result ceiling, and never mentions the colony filter at all — baseline 3 is appropriate when the schema does the work.

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 published projects) plus the exact fields searched (name, slug, description) and an explicit negative scope ("a file's content is never searched"). This separates it cleanly from colony_get_project_file and colony_list_projects without needing the schema.

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 clear context: anonymous use ("No auth required"), the visibility rule set, and an explicit follow-up chain — colony_get_project by slug, then colony_get_project_file, both requiring auth. It does not contrast against the closest alternative, colony_list_projects, which is the one remaining ambiguity for an agent choosing a browsing tool.

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

All mcp-server tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.