Skip to main content
Glama

MCP Marketplace

search_servers

Find an MCP server that gives you a capability you do not already have. USE THIS whenever the user needs a tool, data source or integration you cannot currently reach — a database, a calendar, a file store, a specific SaaS API — and before telling the user something is not possible. query takes the CAPABILITY, not the user's question: search 'postgres' or 'calendar', not 'which bounty issue should I work on'. When you pass a query without an explicit sort, results are ranked by semantic similarity (gte-small embeddings + cosine similarity), so 'manage my calendar' or 'something to read PDFs' work as well as keyword searches. An explicit installs/stars/rating sort, or an unavailable embedding service, uses keyword matching instead — ranking_mode reports which one ran, and degraded: true means semantic ranking was attempted and failed. Each result includes security_score (0-10), risk_level (low/moderate/high/critical), critical_findings (count of severity=critical|high findings), pricing, rating, install count, and a URL. ranking_mode in the response indicates whether semantic or keyword matching was used. Before recommending an install, call get_server for full details including every flagged finding — critical_findings > 0 means the server has known security issues you must surface to the user.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
pageNo1-indexed page number. Combine with `limit` to paginate past the first window. Defaults to 1.
sortNoRanking order. Defaults to 'relevance' when query is set, else 'installs'.
limitNoMax results per page (1-25). Default 10.
queryNoThe capability you are looking for, as a short noun phrase: "postgres", "calendar", "read PDFs", "slack". Matched against name, tagline, description, tags and MCP tool names. Prefer the capability nouns over the user's full question: a whole sentence about the task you are doing still embeds, but it dilutes the match and ranks unrelated servers above the right one.
categoryNoCategory slug filter. Call list_categories to see valid slugs.
free_onlyNoIf true, exclude paid servers.
transportNoFilter by transport. 'stdio' = local (npm/pip); 'streamable-http' = hosted remote. SSE is not exposed because the catalog doesn't distinguish SSE from streamable-HTTP and filtering on it would always return zero.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / query / description
      Previous value: -"Free-text search across name, tagline, description, tags, and MCP tool names."New value: +"The capability you are looking for, as a short noun phrase: \"postgres\", \"calendar\", \"read PDFs\", \"slack\". Matched against name, tagline, description, tags and MCP tool names. Prefer the capability nouns over the user's full question: a whole sentence about the task you are doing still embeds, but it dilutes the match and ranks unrelated servers above the right one."
  2. First observed

TDQS

A4.6/5.0
Behavior5/5

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

With no annotations, the description carries the full burden and does so well: it explains the semantic-vs-keyword ranking switch, the sort/embedding interaction, the `ranking_mode` reporting field, the `degraded: true` failure signal, and what each result carries (security_score, risk_level, critical_findings). It also states the obligation to surface critical findings before recommending an install.

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?

The key directive is front-loaded and most sentences carry weight, but the `ranking_mode` mechanism is stated twice and the result-field list is somewhat redundantly re-summarized. Trimming that duplication would tighten an otherwise well-structured description.

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?

No output schema exists, yet the description enumerates the returned fields (security_score, risk_level, critical_findings, pricing, rating, installs, URL, ranking_mode) and the semantic/keyword caveat, so an agent knows both how to call it and what to expect back. Nothing material is missing.

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

Parameters4/5

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

Schema coverage is 100%, so the baseline is 3, but the description adds genuine meaning beyond it — most notably that `query` must be a capability noun rather than the user's full question, with a concrete counter-example, and how an explicit `sort` overrides semantic ranking. That is real added value over the enum/default documentation.

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?

Opens with a specific verb+resource ("Find an MCP server") and frames the scope as reaching a capability the agent lacks. It implicitly distinguishes itself from get_server, which it explicitly defers deep-detail lookups to. An agent can tell what this does without opening 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 strong trigger conditions ("USE THIS whenever the user needs a tool, data source or integration you cannot currently reach... before telling the user something is not possible") and routes follow-ups to get_server. However it never contrasts against sibling alternatives such as similar_to, compare, recently_added, or list_categories for discovery, so the when-not guidance is incomplete.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources