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 ?
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.
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.
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.
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?
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"
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.
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.
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.
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?
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.
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.
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.
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.
- 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.
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.
what is your experience with non trivial db schemas?
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"
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.
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?
MCP is the new IoT, where S stands for security /s
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.
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.
It's also Python.
How do you handle PII or other sensitive data that the LLM shouldn’t know or care about?
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.