query_knowledge_base¶
Semantic search over the project's configured knowledge base (product docs, policy pages, internal wiki). Scoped to the project's configured domains. Returns excerpts with source URLs. If the project hasn't enabled a knowledge base, returns an error explaining so.
Parameters¶
| Parameter | Type | Required | Default | Description |
|---|---|---|---|---|
query |
string | yes | — | Search query (natural language). |
limit |
integer | no | 5 |
Max results. Default: 5. |
Example call¶
from fastmcp import Client
from fastmcp.client.auth import BearerAuth
async with Client(
"https://mcp.chordia.ai/mcp",
auth=BearerAuth("YOUR_APPLICATION_KEY"),
) as client:
result = await client.call_tool(
"query_knowledge_base",
{
"query": "your search text"
},
)
print(result.content[0].text)
# Plus any of the 1 optional params from the table above.
In Claude Desktop, Cursor, or any MCP-aware client the same call is issued by the LLM automatically once the server is configured — see integrations.
Result¶
Success responses are JSON of the shape below. Optional fields are omitted when the underlying data isn't present.
{
"items": [
{
"kb_id": "kb_001",
"title": "Refund policy",
"snippet": "Customers may request a refund within 30 days...",
"score": 0.87
}
],
"count": 1
}
Auth context¶
Every call receives the connection's project_id and access_scope
automatically — the caller never passes them. See
Authentication & RBAC for how scope narrows
results.
Errors¶
All tools return JSON. Errors are wrapped in { "error": "..." }. The
most common shapes are documented in
Python integration → Error shape.