Skip to main content
Glama

meta-agent-tools

by com.agentalog
OverviewDiscussionsAdmin

List listings

list_listings
Read-onlyIdempotent

Public mosaic of live MCP servers, skills, plugins and OKF knowledge bundles. live listings first and the low tail (few stars or no clear license) after them in every order — low=0 leaves the tail out. To walk everything, follow next: without q it is a cursor (next_cursor, keyset on the order's index) and has no ceiling; every listing also has an HTML page at /l/:id and the shards of /sitemap-listings.xml list them all. q runs on a full-text index (FTS5, bm25) kept in the same transaction as every text write. With q and low=0, low_count says how many low listings the filter left out — LIKE with a cap of 200. The query is mapped onto kind/topic/transport filters unless interpret=0.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
qNoFree text over the name, the tagline, the description, the origin identifier and the README excerpt: every word (up to six, 2+ letters, accents ignored) must match; ranked by bm25 with the name weighing most (10), then tagline (5), identifier (3), description (2), README excerpt (1); ties by stars. Kind, topic and transport words become filters. The `low` tail is in the same index.
lowNo`0` leaves the `low` tail out; by default it comes after the `live` listings in every order.
kindNoWhich kind of resource to fetch.
sortNoResult order. Without it, a query is ranked by relevance — bm25 over the full-text index (name 10, tagline 5, identifier 3, description 2, README excerpt 1) multiplied by 1 + 0.05·ln(1 + stars) + 0.1 if pushed in the last 180 days + 0.1 if a README was collected; ties by stars — and a plain listing by arrival.relevancia when q is set, recent otherwise
api_passNoMAT-only private pass: mat_<32 random hex>_<64 random hex>. Generate and save before buying.
categoryNoCategory declared by whoever published.
interpretNo`0` disables query understanding and searches the raw string.
retry_keyNoOptional retry key, up to 80 ASCII characters; same read for five minutes.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • addedInput schema / properties / api_pass
      Added value: +{
+  "description": "MAT-only private pass: mat_<32 random hex>_<64 random hex>. Generate and save before buying.",
+  "type": "string"
+}
    • addedInput schema / properties / retry_key
      Added value: +{
+  "description": "Optional retry key, up to 80 ASCII characters; same read for five minutes.",
+  "type": "string"
+}
  2. Changed3 schema fields changed
    • changedInput schema / properties / low / description
      Previous value: -"`1` includes `low` listings in the result. Only valid together with `q`."New value: +"`0` leaves the `low` tail out; by default it comes after the `live` listings in every order."
    • changedInput schema / properties / low / enum
      Previous value: -[
-  "1"
-]New value: +[
+  "0"
+]
    • changedInput schema / properties / q / description
      Previous value: -"Free text over the name, the tagline, the description, the origin identifier and the README excerpt: every word (up to six, 2+ letters, accents ignored) must match; ranked by bm25 with the name weighing most (10), then tagline (5), identifier (3), description (2), README excerpt (1); ties by stars. Kind, topic and transport words become filters. The `low` tail still uses LIKE."New value: +"Free text over the name, the tagline, the description, the origin identifier and the README excerpt: every word (up to six, 2+ letters, accents ignored) must match; ranked by bm25 with the name weighing most (10), then tagline (5), identifier (3), description (2), README excerpt (1); ties by stars. Kind, topic and transport words become filters. The `low` tail is in the same index."
  3. Changed1 schema field changed
    • changedInput schema / properties / sort / description
      Previous value: -"Result order. Without it, a query is ranked by relevance and a plain listing by arrival."New value: +"Result order. Without it, a query is ranked by relevance — bm25 over the full-text index (name 10, tagline 5, identifier 3, description 2, README excerpt 1) multiplied by 1 + 0.05·ln(1 + stars) + 0.1 if pushed in the last 180 days + 0.1 if a README was collected; ties by stars — and a plain listing by arrival."
  4. Changed1 schema field changed
    • changedInput schema / properties / q / description
      Previous value: -"Free text over the name, the tagline and the description. Kind, topic and transport words become filters."New value: +"Free text over the name, the tagline, the description, the origin identifier and the README excerpt: every word (up to six, 2+ letters, accents ignored) must match; ranked by bm25 with the name weighing most (10), then tagline (5), identifier (3), description (2), README excerpt (1); ties by stars. Kind, topic and transport words become filters. The `low` tail still uses LIKE."
  5. Changed3 schema fields changed
    • changedInput schema / properties / sort / default
      Previous value: -"recent"New value: +"relevancia when q is set, recent otherwise"
    • changedInput schema / properties / sort / description
      Previous value: -"Result order."New value: +"Result order. Without it, a query is ranked by relevance and a plain listing by arrival."
    • changedInput schema / properties / sort / enum
      Previous value: -[
-  "recent",
-  "likes",
-  "visits"
-]New value: +[
+  "relevancia",
+  "recent",
+  "stars",
+  "likes",
+  "visits",
+  "nome"
+]
  6. Changed2 schema fields changed
    • addedInput schema / properties / interpret
      Added value: +{
+  "description": "`0` disables query understanding and searches the raw string.",
+  "enum": [
+    "0"
+  ],
+  "type": "string"
+}
    • changedInput schema / properties / q / description
      Previous value: -"Free text over the name, the tagline and the description."New value: +"Free text over the name, the tagline and the description. Kind, topic and transport words become filters."
  7. Changed9 schema fields changed
    • addedInput schema / properties / category / description
      Added value: +"Category declared by whoever published."
    • addedInput schema / properties / kind / description
      Added value: +"Which kind of resource to fetch."
    • addedInput schema / properties / kind / enum
      Added value: +[
+  "mcp",
+  "skill",
+  "plugin"
+]
    • addedInput schema / properties / low / description
      Added value: +"`1` includes `low` listings in the result. Only valid together with `q`."
    • addedInput schema / properties / low / enum
      Added value: +[
+  "1"
+]
    • addedInput schema / properties / q / description
      Added value: +"Free text over the name, the tagline and the description."
    • addedInput schema / properties / sort / default
      Added value: +"recent"
    • addedInput schema / properties / sort / description
      Added value: +"Result order."
    • addedInput schema / properties / sort / enum
      Added value: +[
+  "recent",
+  "likes",
+  "visits"
+]
  8. First observed

TDQS

A3.6/5.0
Behavior4/5

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

Annotations already cover the read-only/idempotent/non-destructive profile, yet the description adds substantive behavior: the `low` tail is always ordered after `live` results, the cursor is keyset-based with no ceiling, FTS5 is kept in the same transaction as text writes, and `low_count` is a LIKE with a 200 cap. These are non-obvious traits an agent cannot get from annotations alone.

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

Conciseness3/5

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

The opening states the purpose first, but the single dense block then mixes filtering behavior, cursor mechanics, implementation internals (FTS5, bm25, keyset), and tangential facets (HTML pages at /l/:id, the sitemap XML shards) that an agent calling this tool does not need. Several sentences are informative but the whole is longer and more jargon-laden than necessary.

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?

With no output schema, the description carries the burden of explaining the return surface, and it does name the cursor field (`next_cursor`) and `low_count`. Combined with coverage of ordering, filtering, and tail behavior for an 8-parameter, zero-required tool, it is close to sufficient, though it never states what a listing record contains.

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 all eight parameters in detail, including the bm25 weighting and retry_key window. The description largely restates those semantics rather than adding new meaning, which is the baseline-3 case; only the `q` + `low=0` → `low_count` interaction adds novel framing.

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

Purpose4/5

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

The opening sentence names the resource concretely: 'Public mosaic of live MCP servers, skills, plugins and OKF knowledge bundles,' and the schema's kind enum confirms the scope. It does not, however, distinguish this tool from siblings like list_mcp_servers, mcp_index_search, or search_bundles, so an agent must infer the boundary.

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

Usage Guidelines3/5

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

It gives real operational guidance — follow `next` to walk everything, `low=0` to drop the tail, `interpret=0` to disable query understanding — but never states when to choose this tool over the sibling search/list tools. Usage is implied through option behavior rather than routed explicitly.

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

All meta-agent-tools 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