nodebb-mcp

Search the forum

search_forum

Read-only

Search NodeBB forum topics and posts for keywords. Returns ranked matches with snippets, and falls back to scanning recent titles without a search plugin.

Instructions

Full-text search across topic titles and post bodies. Returns ranked matches with a snippet showing why each matched. Requires a search plugin on the forum (NodeBB core has none); when one is absent this falls back to scanning recent topics by title and says so. For answering a question, prefer find_answers, which also extracts the answers.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "query": "<query>"
    },
    "name": "search_forum"
  }
}

Input Schema

Name	Required	Description
`in`	No	Where to look. Default titlesposts (titles and post bodies).
`page`	No	Result page, for paging past the first set.
`tags`	No	Only topics carrying all of these tags.
`limit`	No	Maximum results. Default 15.
`query`	Yes	What to search for. Plain words work best; quotes are not special.
`sort_by`	No	Ordering. Default relevance.
`posted_by`	No	Only posts by this username.
`categories`	No	Restrict to these category ids.
`within_days`	No	Only content newer than this many days.

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Sep 13, 2026

TDQS

A4.5/5.0

Behavior4/5

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

Annotations already declare readOnlyHint and openWorldHint, but the description adds real behavioral context beyond them: the dependency on a search plugin, the fallback to title-only scanning of recent topics, and the fact that the tool announces when it is degraded. It does not cover rate limits or result-count behavior, but this is well above the annotation baseline.

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 sentences, front-loaded with the core capability, then the caveat, then the alternative. No sentence is redundant and every one carries information an agent needs.

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, so the description correctly compensates by describing the return shape ('ranked matches with a snippet showing why each matched'). Combined with the fallback disclosure and sibling routing, an agent has everything required to call and interpret this tool.

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 every parameter carries its own description, so the baseline is 3. The description mentions ranked matches with snippets but adds no syntax or defaults for 'in', 'sort_by', or 'within_days' beyond what the schema already states.

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 ('Full-text search across topic titles and post bodies') and immediately distinguishes itself from the sibling find_answers. An agent can identify what this does and how it differs from alternatives without opening any schema.

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?

Explicitly names the alternative ('For answering a question, prefer find_answers, which also extracts the answers') and gives the condition that selects it. It also documents the degraded-mode scenario, telling the agent when this tool silently behaves differently.

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

Deploy Server