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

ragflow-kb-mcp

by feci
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Hybrid

ragflow_create_search_app

Create a search app with dataset and document IDs, search settings, and optional filters so completion requests can return grounded answers from selected knowledge sources.

Instructions

Create a search app; pass dataset_ids so ragflow_search_app_completion can answer from them.

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": {
      "name": "<name>"
    },
    "name": "ragflow_create_search_app"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameYesSearch app name (unique, max 255 bytes)
top_kNoCandidates considered before reranking
use_kgNoAlso search the knowledge graph
keywordNoExpand the question with LLM keywords
rerank_idNoRerank model as model_name@factory
chat_modelNoChat model for answers as model_name@factory; default is the tenant's
dataset_idsNoDatasets the search app searches (kb_ids)
descriptionNo
document_idsNoLimit the search to these documents (doc_ids)
search_configNoOther search_config keys to set as-is, e.g. llm_setting
cross_languagesNoAlso translate the question into these languages
meta_data_filterNoMetadata filter applied to the documents
similarity_thresholdNoMinimum similarity for a chunk to count
vector_similarity_weightNoWeight of vector similarity; keyword weight is 1 minus this

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.1

TDQS

A3.5/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=false, destructiveHint=false and openWorldHint=false, so the safety profile is covered structurally. The description's contribution is the functional dependency that the app is only useful to completion once datasets are bound, which is genuine behavioral context, but it omits whether name must be globally unique (only in schema), whether the call is idempotent, and what post-creation state is left behind.

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 tight clause pair with the action first and the key parameter recommendation second; nothing is wasted and the important part is front-loaded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists and the input schema is richly documented, so the description need not describe returns. However, for a 14-parameter creation tool in a large sibling set, the description says nothing about permission requirements, the relationship to list_search_apps/update_search_app, or what to configure beyond dataset_ids, leaving the agent to mine the schema.

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 93%, so nearly every one of the 14 parameters is already documented, including dataset_ids as 'Datasets the search app searches (kb_ids)'. The description singles out dataset_ids as the important one for downstream use, which adds a small prioritization signal, but adds no syntax, defaults, or trade-off guidance for top_k, use_kg, rerank_id or search_config.

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?

States a specific verb and resource ('Create a search app') and names the sibling consumer (ragflow_search_app_completion) that makes the artifact useful, so the agent understands what is being produced. It stops short of distinguishing this from other creation siblings like ragflow_create_chat or ragflow_create_agent, which produce superficially similar objects.

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 through the workflow hint that dataset_ids should be supplied so ragflow_search_app_completion can answer from them, which effectively tells the agent this is a setup step. There is no explicit when-to-use versus a chat/agent, no prerequisites (do datasets need to exist first?), and no guidance for the case where dataset_ids is omitted.

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