Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.knowledgestack.ai/llms.txt

Use this file to discover all available pages before exploring further.

GitHub PyPI knowledgestack-mcp is a read-side MCP server. It exposes ten tools for searching, listing, and reading documents in your tenant. Plug it into any MCP-speaking client — LangChain, LangGraph, CrewAI, Temporal, OpenAI Agents SDK, pydantic-ai, Claude Desktop, Cursor — without framework-specific glue.

​
Install & run

uvx knowledgestack-mcp

​
Configure

export KS_API_KEY="sk-user-..."
export KS_BASE_URL="https://api.knowledgestack.ai"   # optional

​
Plug into your agent framework

from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerStdio

mcp = MCPServerStdio(
    command="uvx",
    args=["knowledgestack-mcp"],
    env={"KS_API_KEY": os.environ["KS_API_KEY"]},
)
agent = Agent(model="openai:gpt-4o", mcp_servers=[mcp], output_type=MyOutput)

​
Tools (v1, read-only)

ToolPurpose
list_contentschildren of a folder
findfuzzy name search
get_infometadata + ancestry breadcrumb
readfull text of a path-part with [chunk:<uuid>] markers
read_aroundchunks before/after an anchor
view_chunk_imageimage-chunk bytes
search_knowledgedense-vector semantic search
search_keywordBM25 keyword search
get_organization_infotenant metadata
get_current_datetimeUTC + tenant-local datetime
Writes are intentionally not exposed in v1.

​
Cookbook

32 production-style flagships using this MCP server across banking, legal, healthcare, insurance, real estate, sales, HR, engineering, government, pharma, and energy: knowledgestack/ks-cookbook.