Skip to main content
Glama
Sign In

Vibe Shipped

by io.github.sorindecu
OverviewDiscussionsAdmin

Find a verified tool for a task

find_tool_for_task
Read-onlyIdempotent

Find or search for an MCP server, connector, integration, agent or skill for a task (e.g. query Postgres, automate a browser, take payments, send email). Returns the top 3 verified working options with a one-line install, in about 3 KB. Example: {"task":"query a Postgres database"}

Input Schema

NameRequiredDescriptionDefault
taskNoWhat the user wants to do or connect to, in their words: find an MCP server, connector, plugin or integration for a service or job, e.g. "query Postgres", "connector for Jira", "send email", "scrape a website".
limitNoResults.
clientNoOptional: client to install into (claude, claude-code, cursor, chatgpt, vscode, hermes) for a matching install snippet or config.
fieldsNoOnly these keys of the full record, e.g. ["install","source"].
verboseNoFull records (lead, source, verification, all snippets).
industryNoOptional: the user's industry, e.g. legal, finance, healthcare. Only for anonymous usage stats; does not change results.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / properties / client / description
      Previous value: -"Optional: your client (claude, cursor, chatgpt, hermes) for a client-specific install snippet."New value: +"Optional: client to install into (claude, claude-code, cursor, chatgpt, vscode, hermes) for a matching install snippet or config."
    • changedInput schema / properties / task / description
      Previous value: -"The job you need a tool, MCP server or integration for, in plain words, e.g. \"query a Postgres database\"."New value: +"What the user wants to do or connect to, in their words: find an MCP server, connector, plugin or integration for a service or job, e.g. \"query Postgres\", \"connector for Jira\", \"send email\", \"scrape a website\"."
  2. Changed1 schema field changed
    • changedInput schema / properties / task / description
      Previous value: -"The task in plain words, e.g. \"query a Postgres database\"."New value: +"The job you need a tool, MCP server or integration for, in plain words, e.g. \"query a Postgres database\"."
  3. Changed1 schema field changed
    • addedInput schema / properties / industry
      Added value: +{
+  "description": "Optional: the user's industry, e.g. legal, finance, healthcare. Only for anonymous usage stats; does not change results.",
+  "type": "string"
+}
  4. Changed3 schema fields changed
    • changedInput schema / properties / client / description
      Previous value: -"Your client, so install is a snippet for it."New value: +"Optional: your client (claude, cursor, chatgpt, hermes) for a client-specific install snippet."
    • removedInput schema / properties / client / enum
      Removed value: -[
-  "claude",
-  "cursor",
-  "chatgpt",
-  "hermes"
-]
    • removedInput schema / required
      Removed value: -[
-  "task"
-]
  5. Changed4 schema fields changed
    • changedInput schema / properties / client / description
      Previous value: -"Your client, so install is a snippet for it. Omit for snippets for every client."New value: +"Your client, so install is a snippet for it."
    • addedInput schema / properties / fields
      Added value: +{
+  "description": "Only these keys of the full record, e.g. [\"install\",\"source\"].",
+  "items": {
+    "type": "string"
+  },
+  "type": "array"
+}
    • addedInput schema / properties / limit
      Added value: +{
+  "default": 3,
+  "description": "Results.",
+  "maximum": 5,
+  "minimum": 1,
+  "type": "integer"
+}
    • addedInput schema / properties / verbose
      Added value: +{
+  "default": false,
+  "description": "Full records (lead, source, verification, all snippets).",
+  "type": "boolean"
+}
  6. Added

TDQS

A3.9/5.0
Behavior4/5

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

Annotations already declare readOnly, idempotent, non-destructive, and non-open-world, so the safety profile is covered. The description adds value beyond that by disclosing the result contract: exactly three 'verified working' options, an install snippet, and a payload budget of roughly 3 KB, which tells the agent the response is deliberately small and pre-validated.

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?

Three compact sentences, front-loaded with the capability, then the return contract, then a concrete example. 'Find or search for' is mildly redundant, and the parenthetical service list overlaps with the schema's examples, but nothing is wasted.

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?

All six parameters are optional and fully documented in the schema, and no output schema exists, so the description carries the burden of describing returns — which it does by naming the top-3 verified options, the one-line install, and the size ceiling. The remaining gap is the lack of any routing guidance toward the many sibling tools.

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 baseline is 3. The description only lightly reinforces parameters — 'top 3' maps to the default limit, and 'about 3 KB' versus full records hints at the verbose/fields tradeoff — but it never explains limit, fields, client, or industry beyond what the schema already says.

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 (find/search) and a specific resource class (MCP server, connector, integration, agent, skill) plus the use case framing 'for a task'. It also previews the result shape — top 3 verified working options with a one-line install — so the agent knows exactly what it gets back, and an inline example anchors the pattern.

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?

Usage is implied by the 'for a task' framing and the sample tasks (query Postgres, automate a browser, take payments, send email), which show the right granularity of query. However, no alternatives are named: siblings like search_apps, get_tool, or compare_tools are never mentioned, so the agent must infer when this differs from a plain app search.

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

All Vibe Shipped toolsInspect
Try in Browser
Claude Code, inside the Godot 4 editorFlockbay puts an AI agent in the real Godot 4 editor: it writes GDScript, runs your game and fixes what breaks. Free, or bring your own Claude Code or Codex.flockbay.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources