How to Use the Glean MCP in Pydantic AI

Q: How does Pydantic AI ensure my indexed files and collection lists remain private?

Every transaction involving bulkindexdocuments or listcollections runs through a zero-trust execution layer. The Pydantic AI framework only receives the validated data payloads, and your underlying Glean API tokens are kept entirely out of the application's runtime memory.

Run type-safe, validated enterprise searches using Glean with Pydantic AI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Glean MCP to Pydantic AI

Create your Vinkius account to connect Glean to Pydantic AI and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Glean with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-Safe Search with Pydantic AI

Stop worrying about malformed search outputs breaking your production Pydantic AI code. This MCP Server forces every response from `search` and `search_by_datasource` to conform to strict Python schemas. If the Glean API returns unexpected field types, Pydantic AI rejects the payload before your agent can hallucinate a response. This strict runtime validation is critical when handling sensitive corporate files via Glean. You get clean, predictable data structures that match your Pydantic AI models every single time.

Validated Directory and Org Lookups

Querying employee profiles via Glean requires strict data validation to prevent schema errors in Pydantic AI. Your agent uses `search_people` to find team members and maps the return data directly into your internal user models. If a Glean profile is missing required fields, the framework raises a validation error immediately. You can also verify system availability by running `check_glean_status` before initiating heavy Pydantic AI queries. This keeps your application state predictable even when the Glean API experiences downtime.

Strict Document Indexing and Collection Mapping

Manage your Glean knowledge base without risking database corruption in your Pydantic AI pipelines. The agent uses `index_document` and `bulk_index_documents` to write validated data payloads back to the index. If the document structure doesn't match your Pydantic AI schemas, the write operation is blocked. For reading structures, `list_collections` and `get_collection` return strongly-typed folder trees to Pydantic AI. This ensures your agent always knows the exact format of the Glean data it is processing.

Setup guide

Set up Glean MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "glean-alternative-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Glean tools.",
)

result = await agent.run("List recent Glean transactions")
print(result.output)

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Glean. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Glean now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Glean MCP in Pydantic AI

The framework validates every search result against strict Python types at runtime. This prevents tools like `search` from feeding corrupt or unexpected JSON to your model.

Pydantic AI will raise a validation error instantly, alerting your team. This stops the agent from processing bad data returned by `get_document` or `list_collections`.

Initialize the MCP toolset with the server URL and pass it to your agent's constructor. The agent automatically maps tools like `chat` and `search_people` to validated run methods.

Yes, because the server uses the open MCP standard, any model supported by Pydantic AI can access tools like `check_glean_status` or `search`.

Every transaction involving `bulk_index_documents` or `list_collections` runs through a zero-trust execution layer. The Pydantic AI framework only receives the validated data payloads, and your underlying Glean API tokens are kept entirely out of the application's runtime memory.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript