Show HN: EnrichMCP – A Python ORM for Agents

(github.com)

71 points | by bloppe 5 hours ago

5 comments

  • polskibus 4 hours ago
    This looks very interesting but I’m not sure how to use it well. Would you mind sharing some prompts that use it and solve a real problem that you encountered ?
    • simba-k 3 hours ago
      Imagine you're building a support agent for DoorDash. A user asks, "Why is my order an hour late?" Most teams today would build a RAG system that surfaces a help center article saying something like, "Here are common reasons orders might be delayed."

      That doesn't actually solve the problem. What you really need is access to internal systems. The agent should be able to look up the order, check the courier status, pull the restaurant's delay history, and decide whether to issue a refund. None of that lives in documentation. It lives in your APIs and databases.

      LLMs aren't limited by reasoning. They're limited by access.

      EnrichMCP gives agents structured access to your real systems. You define your internal data model using Python, similar to how you'd define models in an ORM. EnrichMCP turns those definitions into typed, discoverable tools the LLM can use directly. Everything is schema-aware, validated with Pydantic, and connected by a semantic layer that describes what each piece of data actually means.

      You can integrate with SQLAlchemy, REST APIs, or custom logic. Once defined, your agent can use tools like get_order, get_restaurant, or escalate_if_late with no additional prompt engineering.

      It feels less like stitching prompts together and more like giving your agent a real interface to your business.

      • dakiol 47 minutes ago
        Why wouldn't we just give the agent read permission on a replica db? Wouldn't that be enough for the agent to know about:

        - what tables are there

        - table schemas and relationships

        Based on that, the agent could easily query the tables to extract info. Not sure why we need a "framework" for this.

        • RobertDeNiro 4 minutes ago
          Because you also need proper access controls. In many cases database access is too low level, you need to bring it up a layer or two to know who can access what. Even more so when you want to do more than read data.
        • robmccoll 35 minutes ago
          Disclaimer: I don't know the details of how this works.

          Time-to-solution and quality would be my guess. In my experience, adding high level important details about the way information is organized to the beginning of the context and then explaining the tools to further explore schema or access data produces much more consistent results rather than each inference having to query the system and build its own world view before trying to figure out how to answer your query and then doing it.

          It's a bit like giving you a book or giving you that book without the table of contents and no index, but you you can do basic text search over the whole thing.

      • polskibus 2 hours ago
        are you saying that a current gen LLM can answer such queries with EnrichMCP directly? or does it need guidance via prompts (for example tell it which tables to look at, etc. ) ? I did expose a db schema to LLM before, and it was ok-ish, however often times the devil was in the details (one join wrong, etc.), causing the whole thing to deliver junk answers.

        what is your experience with non trivial db schemas?

        • simba-k 1 hour ago
          So one big difference is that we aren't doing text2sql here, and the framework requires clear descriptions on all fields, entities, and relationships (it literally won't run otherwise).

          We also generate a few tools for the LLM specifically to explain the data model to it. It works quite well, even on complex schemas.

          The use case is more transactional than analytical, though we've seen it used for both.

          I recommend running the openai_chat_agent in examples/ (also supports ollama for local run) and connect it to the shop_api server and ask it a question like : "Find and explain fraud transactions"

          • polskibus 1 hour ago
            So explicit model description (kind of repeating the schema into explicit model definition) provides better results when used with LLM because it’s closer to the business domain(or maybe the extra step from DDL to business model is what confuses the LLM?). I think I’m failing to grasp why does this approach work better than straight schema fed to Llm.
      • skuenzli 3 hours ago
        This is the motivating example I was looking for on the readme: a client making a request and an agent handling it using the MCP. Along with a log of the agent reasoning its way to the answer.
        • simba-k 1 hour ago
          Yes but the agent reasoning is going to use an LLM, I sometimes run our openai_chat_agent example just to test things out. Try giving it a shot, ask it to do something then ask it to explain its tool use.

          Obviously, it can (and sometimes will) hallucinate and make up why its using a tool. The thing is, we don't really have true LLM explainability so this is the best we can really do.

      • TZubiri 56 minutes ago
        Cool. Can you give the agent a db user with restricted read permissions?

        Also, generic db question, but can you protect against resource overconsumption? Like if the junior/agent makes a query with 100 joins, can a marshall kill the process and time it out?

      • Sytten 1 hour ago
        This is opening a new can of worm of information disclosure, at least one job the AI won't kill is people in security.

        MCP is the new IoT, where S stands for security /s

        • TZubiri 53 minutes ago
          What is the difference between a junior and an agent. Can't you give them smart permissions on a need to know basis?

          I guess you also need per user contexts, such that you depend on the user auth to access user data, and the agent can only access that data.

          But this same concern exists for employees in big corps. If I work at google, I probably am not able to access arbitrary data, so I can't leak it.

      • smohare 1 hour ago
        [dead]
  • aolfat 4 hours ago
    Woah, it generates the SQLAlchemy automatically? How does this handle auth/security?
    • simba-k 4 hours ago
      Yep, we can essentially convert from SQLAlchemy into an MCP server.

      Auth/Security is interesting in MCP. As of yesterday a new spec was released with MCP servers converted to OAuth resource servers. There's still a lot more work to do on the MCP upstream side, but we're keeping up with it and going to have a deeper integration to have AuthZ support once the upstream enables it.

  • knowsuchagency 4 hours ago
    Super interesting idea. How feasible would it be to integrate this with Django?
    • simba-k 4 hours ago
      Very! We had quite a few people do this at a hackathon we hosted this past weekend.
  • revskill 3 hours ago
    Do you provide prisma alternative ?
    • simba-k 3 hours ago
      Not sure exactly what you mean here. Prisma is an ORM for developers working with databases in TypeScript. EnrichMCP is more like an ORM for AI agents. It’s not focused on replacing Prisma in your backend stack, but it serves a similar role for agents that need to understand and use your data model.

      It's also Python.

  • ljm 1 hour ago
    > agents query production systems

    How do you handle PII or other sensitive data that the LLM shouldn’t know or care about?

    • traverseda 1 hour ago
      That's an odd question. If you have a regular ORM how do you handle sensitive data that your user shouldn't know about? You add some logic or filters so that the user can only query their own data, or other data they have permission to access.

      It's also addressed directly in the README. https://github.com/featureform/enrichmcp?tab=readme-ov-file#...

      I know LLMs can be scary, but this is the same problem that any ORM or program that handles user data would deal with.