DEDUPED Hot AI repos, turned into use cases Get 5 a day

How to ask an AI agent questions over dated filings with Qanat

Connect an MCP client to Qanat's read-only research scope and query SEC filings and screens in plain language.

  • Money
  • Intermediate
  • 30 minutes
  • From the README
  • Any agent

Who it is forAn analyst who wants an AI agent to read company data and screen results directly, without writing queries.

The problemPulling figures from many 10-K filings by hand is slow, and an agent without dated data may answer using information that was not yet public.

The outcomeAn agent that answers questions about what data is in the project, where it came from, and which companies passed a rule in a given year, using only dated data.

What you need first

  • Python 3.10 or newer
  • uv or pip to install qanat-fdtl
  • A contact email for the SEC_USER_AGENT setting, which the SEC uses to identify requests (no API key or account)
  • An MCP-capable agent client, only for the agent use case

Steps

  1. Install Qanat with uv tool install qanat-fdtl (or pip install qanat-fdtl).
  2. Set your contact address with export SEC_USER_AGENT="your name [email protected]".
  3. Create a demo project with qanat init my-research --demo && cd my-research.
  4. Register the server with your agent using claude mcp add qanat -- qanat mcp --scope research, or add the Qanat entry with cwd set to the project folder in any MCP client.
  5. Ask the agent: "Which companies passed my rule in 2022?"

Prompt for your agent

Using the qanat MCP server in <project-folder> with research scope, answer this question: <question>. Reply with the answer, the source filings or tables used, and the dates they were public. Verify that every number comes from a Qanat tool call and not from memory.

Caveat. The dates protect a step but not the person or agent asking, so the agent can still see later data while exploring, and results must be checked for timing.

Share: X LinkedIn Hacker News Email Copy link

Disclaimer

Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page