Skip to main content
Glama

CNAPS.ai MCP Server

by ai.cnaps.mcp
OverviewDiscussionsAdmin

search_community

Read-onlyIdempotent

Search community-shared AI flows on cnaps.ai. Find flows by keyword, input/output modality, or tags. Use this to discover existing flows before creating new ones. Returns post IDs that can be forked with fork_community_flow.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
sortNoSort order: 'popular' (default), 'recent', 'most_liked', 'most_forked'.
tagsNoFilter by tags (AND logic). JSON array or comma-separated, e.g. '["upscale","4k"]' or 'upscale,4k'.
queryNoSearch keyword (e.g., 'super resolution', 'background removal', 'deblur'). Searches titles, content, and tags.
cursorNoCursor for the next page. Omit for the first page; for later pages pass next_cursor from the previous response unchanged. Keep query, sort and filters the same while paging — changing any of them starts the search over at the first page, without an error. Each page is 20 results, and the response has no next_cursor on the last one.
input_typeNoFilter by input modality: image, text, video, or sound. JSON array or comma-separated, e.g. '["image","video"]' or 'image,video'. A list matches flows whose inputs are exactly that set — image and video means both, not either.
output_typeNoFilter by output modality: image, text, video, or sound. JSON array or comma-separated, e.g. '["image","video"]' or 'image,video'. A list matches flows whose outputs are exactly that set — image and video means both, not either.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changed
    • addedInput schema / properties / cursor
      Added value: +{
+  "description": "Cursor for the next page. Omit for the first page; for later pages pass next_cursor from the previous response unchanged. Keep query, sort and filters the same while paging — changing any of them starts the search over at the first page, without an error. Each page is 20 results, and the response has no next_cursor on the last one.",
+  "type": "string"
+}
    • changedInput schema / properties / input_type / description
      Previous value: -"Filter by input modality: image, text, video, or sound. A comma-separated list matches flows whose inputs are exactly that set — `image,video` means both, not either."New value: +"Filter by input modality: image, text, video, or sound. JSON array or comma-separated, e.g. '[\"image\",\"video\"]' or 'image,video'. A list matches flows whose inputs are exactly that set — image and video means both, not either."
    • changedInput schema / properties / output_type / description
      Previous value: -"Filter by output modality: image, text, video, or sound. A comma-separated list matches flows whose outputs are exactly that set — `image,video` means both, not either."New value: +"Filter by output modality: image, text, video, or sound. JSON array or comma-separated, e.g. '[\"image\",\"video\"]' or 'image,video'. A list matches flows whose outputs are exactly that set — image and video means both, not either."
    • removedInput schema / properties / page
      Removed value: -{
-  "description": "Page number, 1-5 (default: 1). Each page is 20 results; past page 5, narrow the query or filters instead.",
-  "type": "number"
-}
  2. Changed3 schema fields changed
    • changedInput schema / properties / input_type / description
      Previous value: -"Filter by input modality. Comma-separated: image, text, video, sound."New value: +"Filter by input modality: image, text, video, or sound. A comma-separated list matches flows whose inputs are exactly that set — `image,video` means both, not either."
    • changedInput schema / properties / output_type / description
      Previous value: -"Filter by output modality. Comma-separated: image, text, video, sound."New value: +"Filter by output modality: image, text, video, or sound. A comma-separated list matches flows whose outputs are exactly that set — `image,video` means both, not either."
    • changedInput schema / properties / page / description
      Previous value: -"Page number (default: 1)."New value: +"Page number, 1-5 (default: 1). Each page is 20 results; past page 5, narrow the query or filters instead."
  3. Changed1 schema field changed
    • changedInput schema / properties / tags / description
      Previous value: -"Filter by tags. Comma-separated (AND logic)."New value: +"Filter by tags (AND logic). JSON array or comma-separated, e.g. '[\"upscale\",\"4k\"]' or 'upscale,4k'."
  4. First observed

TDQS

A4/5.0
Behavior3/5

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

Annotations already declare readOnly, idempotent, non-destructive, closed-world, so the safety profile is fully covered. The description's one extra fact — that results are post IDs forkable via fork_community_flow — is useful linkage, but there is no output schema to explain the response shape and no note on rate limits or auth. Adequate but not rich.

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

Conciseness5/5

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

Three short sentences, front-loaded with what the tool is, then how to use it, then what it returns. No filler, no restating of the title.

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

Completeness4/5

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

For a no-required-param search tool with no output schema, the description covers purpose, filters, usage context, and the return type (post IDs). It omits any note on result volume or default behavior beyond pagination already in the schema, which is a minor gap given the annotations already cover safety.

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% and each parameter (sort values, tag syntax, query scope, cursor paging, exact-set modality semantics) is documented in the schema itself. The description only paraphrases 'keyword, input/output modality, or tags' and adds no syntax or edge-case detail beyond the schema.

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 community-shared AI flows on cnaps.ai') and enumerates the three filter dimensions (keyword, modality, tags). It is clearly distinguishable from siblings like list_flows (own flows) and get_community_post (single post).

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?

'Use this to discover existing flows before creating new ones' gives an explicit when-to-use tied to the create workflow. It also names the follow-on tool fork_community_flow. It doesn't state when-not to use it (e.g. versus list_templates or suggest_flow), so it falls short of a 5.

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

All CNAPS.ai MCP Server toolsInspect
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.

Resources