Skip to main content
Glama
Sign In
ragflow-kb-mcp

ragflow-kb-mcp

by feci
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Hybrid

ragflow_search_app_completion

Read-only

Answers questions using a search app’s datasets and an LLM, returning the generated answer with source chunks for verification.

Instructions

Answer a question with a search app's datasets and LLM; returns the answer and its source chunks.

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": {
      "search_id": "<search_id>",
      "question": "<question>"
    },
    "name": "ragflow_search_app_completion"
  }
}

Input Schema

NameRequiredDescriptionDefault
questionYesQuestion, ideally in the documents' language
search_idYesSearch app ID
dataset_idsNoDatasets to use only when the search app has none configured
max_referencesNoReturn at most this many source chunks

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.1

TDQS

A3.6/5.0
Behavior3/5

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

With annotations already declaring readOnlyHint=true, openWorldHint=false, and destructiveHint=false, the description adds useful context that this is a RAG-style completion returning both an answer and source chunks. It does not discuss latency, streaming, or how dataset_ids behaves when the app has configured datasets, though that is partly covered by the schema.

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?

A single compact sentence front-loads the action and mechanism, then states the return value. There is no wasted text.

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?

The description is largely complete for a four-parameter read-only tool: annotations cover safety, the schema covers all parameters, and an output schema exists. The main remaining gap is lack of explicit routing guidance versus sibling retrieval and chat 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 all four parameters are already documented, including when dataset_ids applies and the max_references bound. The description adds no parameter-level detail beyond what the schema provides, so the baseline of 3 is appropriate.

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 description states a specific verb (answer a question) and mechanism (search app's datasets plus LLM), and it notes the return of answer and source chunks. It distinguishes this from retrieval-only or chat tools by tying the operation to a search app, though it does not explicitly name the sibling alternatives.

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?

The usage is implied: use this to get a generated answer from a configured search app. It does not say when to prefer it over ragflow_retrieval, ragflow_chat, or ragflow_openai_chat_completion, nor does it state prerequisites such as requiring an existing search app.

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

Deploy Server

Other Tools