Skip to main content
Glama

docs-mcp

by com.redpanda
OverviewDiscussionsAdmin

Search Redpanda Sources

ask_redpanda_question

Search the official Redpanda documentation and return the most relevant sections from it for a user query. Each returned section includes the url and its actual content in markdown. Use this tool for all queries that require Redpanda knowledge. Results are ordered by relevance, with the most relevant result returned first. If you know the user's deployment platform, pass "platform" so results from the other platform's docs are excluded. Note that "platform" filters the sections already retrieved rather than re-running the search, so it can return substantially fewer sections: on a broker-level question where most matches come from the other platform's docs, it can cut a 15-section response to 1 or 2. Omit "platform" if you would rather have more context and judge platform relevance yourself from each section's url. If you know which Redpanda version the user runs, pass "version" (use 'current' for the latest release; its release number is also accepted). Unlike "platform", "version" is applied during retrieval, so it does not shrink the result set: it stops the same page being returned once per indexed version, which is otherwise most of the response. Version-neutral docs (Cloud, Connect, Agentic Data Plane, API reference) are always included. Omitting "version" searches the latest release.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
top_kNoMaximum number of sections to return, applied after platform filtering. Must be a positive integer.
contextNoOptional. In one concise sentence (third person), describe what the user is trying to accomplish with this request. Do not include credentials, tokens, personal data, or verbatim secrets.
versionNoDocs version to search, written as the docs URLs spell it (23.3, 24.1, 24.2, 24.3, 25.1, 25.2, 25.3, 26.1, current). Use 'current' for the latest release; a release number newer than every listed one is also read as the latest release. Applied at retrieval, so unlike "platform" it does not shrink the result set: every section returned is from this version, plus version-neutral docs (Cloud, Connect, Agentic Data Plane, API reference), which are always included. Omit to search the latest release. Any other value is rejected with the list of valid versions.
platformNoThe user's deployment platform. 'cloud' excludes Self-Managed sections; 'self-managed' excludes Redpanda Cloud sections. Platform-neutral docs (Connect, API reference, labs) are always kept. Applied after retrieval, so it shrinks the result set rather than finding more of the right platform's pages. Omit to search all docs.
questionYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / version
      Added value: +{
+  "description": "Docs version to search, written as the docs URLs spell it (23.3, 24.1, 24.2, 24.3, 25.1, 25.2, 25.3, 26.1, current). Use 'current' for the latest release; a release number newer than every listed one is also read as the latest release. Applied at retrieval, so unlike \"platform\" it does not shrink the result set: every section returned is from this version, plus version-neutral docs (Cloud, Connect, Agentic Data Plane, API reference), which are always included. Omit to search the latest release. Any other value is rejected with the list of valid versions.",
+  "type": "string"
+}
  2. Changed3 schema fields changed
    • addedInput schema / additionalProperties
      Added value: +false
    • changedInput schema / properties / context / description
      Previous value: -"Explain why you are calling this tool and how it fits into the user's overall goal. This parameter is used for analytics and user intent tracking. YOU MUST provide 15-25 words (count carefully). NEVER use first person ('I', 'we', 'you') - maintain third-person perspective. NEVER include sensitive information such as credentials, passwords, or personal data. Example (20 words): \"Searching across the organization's repositories to find all open issues related to performance complaints and latency issues for team prioritization.\""New value: +"Optional. In one concise sentence (third person), describe what the user is trying to accomplish with this request. Do not include credentials, tokens, personal data, or verbatim secrets."
    • changedInput schema / required
      Previous value: -[
-  "question",
-  "context"
-]New value: +[
+  "question"
+]
  3. Changed4 schema fields changed
    • addedInput schema / properties / platform
      Added value: +{
+  "description": "The user's deployment platform. 'cloud' excludes Self-Managed sections; 'self-managed' excludes Redpanda Cloud sections. Platform-neutral docs (Connect, API reference, labs) are always kept. Applied after retrieval, so it shrinks the result set rather than finding more of the right platform's pages. Omit to search all docs.",
+  "enum": [
+    "cloud",
+    "self-managed"
+  ],
+  "type": "string"
+}
    • addedInput schema / properties / top_k / description
      Added value: +"Maximum number of sections to return, applied after platform filtering. Must be a positive integer."
    • addedInput schema / properties / top_k / exclusiveMinimum
      Added value: +0
    • changedInput schema / properties / top_k / type
      Previous value: -"number"New value: +"integer"
  4. Changed3 schema fields changed
    • removedInput schema / additionalProperties
      Removed value: -false
    • addedInput schema / properties / context
      Added value: +{
+  "description": "Explain why you are calling this tool and how it fits into the user's overall goal. This parameter is used for analytics and user intent tracking. YOU MUST provide 15-25 words (count carefully). NEVER use first person ('I', 'we', 'you') - maintain third-person perspective. NEVER include sensitive information such as credentials, passwords, or personal data. Example (20 words): \"Searching across the organization's repositories to find all open issues related to performance complaints and latency issues for team prioritization.\"",
+  "type": "string"
+}
    • changedInput schema / required
      Previous value: -[
-  "question"
-]New value: +[
+  "question",
+  "context"
+]
  5. First observed

TDQS

A5/5.0
Behavior5/5

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

With no annotations provided, the description carries the full burden, and it excels. It discloses that 'platform' filters already-retrieved sections (post-retrieval), which can significantly reduce the result set, and that 'version' is applied during retrieval and does not shrink results. It also explains that version-neutral docs are always included and that results are ordered by relevance. This level of behavioral detail is beyond what the schema provides and is essential for correct invocation.

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?

The description is moderately long but every sentence earns its place. It front-loads the purpose and then systematically explains the two optional parameters with their trade-offs. The structure is logical and scannable, with no redundant or filler content. The length is justified by the need to convey complex filtering behavior.

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?

Given the tool has 5 parameters (1 required), no output schema, and no annotations, the description covers all essential aspects: what it does, how results are ordered, the effect of each filtering parameter, and what is always included. It also addresses the trade-offs of omitting parameters. An agent has enough information to call this tool correctly without needing additional context.

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

Parameters5/5

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

Although the schema already describes each parameter with 80% coverage, the description adds critical semantic nuances. For 'platform', it explains the filtering is applied after retrieval, affecting result count, and suggests omitting it for more context. For 'version', it clarifies the application timing and that it doesn't shrink results. These insights go well beyond the schema's static descriptions and materially help an agent choose parameter values.

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?

The description clearly states the action ('Search'), the resource ('official Redpanda documentation'), and the outcome ('return the most relevant sections'). It also specifies the return format (URL and content in markdown). It distinguishes itself from sibling tools by focusing on general docs rather than API reference, which is evident from the context even though it doesn't name alternatives explicitly.

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

Usage Guidelines5/5

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

The description explicitly says 'Use this tool for all queries that require Redpanda knowledge', which is a direct usage directive. It provides detailed guidance on when to pass 'platform' (when you know the deployment platform) and when to omit it (for more context), and similarly for 'version' (when you know the version, with clarification that it doesn't shrink results). It also explains the trade-offs clearly, so an agent knows exactly when to use this tool and how to tailor parameters.

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

All docs-mcp 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