Skip to content
docs

Pydantic AI and Deedglass

Give a Pydantic AI agent Deedglass’s tools in one file. The file starts Deedglass’s MCP server (npx -y deedglass mcp serve) and hands its tools to the agent: each call goes through your policy, the risky ones wait for a person, and each one is sealed as a deed you can check later.

Tested with pydantic-ai-slim 2.59.0 with the mcp and openai extras, and fastmcp 4.1.3 (2026-10-21).

Before you start

Section titled “Before you start”
  1. In any folder, run npx deedglass init (Docker, about 15 seconds; the quickstart). It starts Deedglass and a demo Postgres with 500 orders, and saves an agent key in .deedglass/quickstart.key.
  2. Run the file below from that folder (or a folder inside it). deedglass mcp serve looks for the key there; from anywhere else, set DEEDGLASS_API_KEY and DEEDGLASS_SERVER yourself (how mcp serve finds them).
  3. Under the postgres-safe policy that init turns on, reads run, DROP and TRUNCATE are refused, and a write waits for a person in Console › Approvals before it runs.

The MCP route

Section titled “The MCP route”
examples/frameworks/pydantic-ai/agent.py
# Run where you ran `npx deedglass init`. Needs OPENAI_API_KEY.
from fastmcp.client.transports import StdioTransport
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPToolset


toolset = MCPToolset(StdioTransport(command="npx", args=["-y", "deedglass", "mcp", "serve"]))
agent = Agent("openai:gpt-6.1-sol", toolsets=[toolset])
print(agent.run_sync("How many rows are in public.orders?").output)

Install and run:

Terminal window
pip install "pydantic-ai-slim[mcp,openai]==2.59.0" fastmcp==4.1.3
python agent.py

Model key: OPENAI_API_KEY (the model string is the one in Pydantic AI’s MCP client page). Any model Pydantic AI supports works.

Tool names: Deedglass lists its tools with names every model API takes: postgres_query, postgres_execute, deedglass_check_approval (letters, digits, _ and -; Anthropic’s rule is ^[a-zA-Z0-9_-]{1,128}$ and OpenAI’s allows the same characters up to 64). Your policies and the sealed records keep the dotted name, postgres.query; Deedglass maps one to the other (MCP.md). Deedglass 0.7 and earlier listed the dotted names, which these APIs refuse.

What you see: the answer (500 rows), and in Console › Ledger or npx deedglass actions list one sealed postgres.query action per call, with the rule that allowed it. If the agent tries a write, the tool answers that it is waiting for approval and nothing has run; once someone approves, deedglass_check_approval lets the agent carry on. A refused call answers with the policy’s sentence and a record id.

First start: npx -y deedglass can take several seconds the first time. If a framework’s MCP connect timeout is shorter, run npx -y deedglass version once first, or install the CLI (INSTALL.md) and use deedglass as the command.

Check it without a model key

Section titled “Check it without a model key”

examples/frameworks/pydantic-ai/ has the file, its pinned packages and a check file that needs no model key: it starts deedglass mcp serve through the same framework client and drives the agent with Pydantic AI’s TestModel, which calls postgres_describe for real, through Deedglass. From the folder where init ran:

Terminal window
path/to/deedglass/examples/frameworks/run.sh pydantic-ai            # install the pins in a temp folder, run the check
path/to/deedglass/examples/frameworks/run.sh pydantic-ai --agent    # also run the agent file when its model key is set

The workflow frameworks.yml runs every check against a fresh init stack each week and on pull requests that touch these files. It isn’t a required check: a framework release that doesn’t install is reported as skipped, not as a failure.

Sources and what isn’t verified

Section titled “Sources and what isn’t verified”

Every framework API in the files above comes from the framework’s own docs, checked 2026-10-21:

Not verified:

  • A run with a live model; the check uses TestModel instead (no model key in CI).