Loading video...

Video Failed to Load

Go Home

Introducing the Knowledge Base MCP. Greptile maintains a detailed knowledge base of how every part of your codebase works, as well as a history of past incidents. Starting today coding agents like Codex, Claude can access the Knowledge Base via Greptile's MCP, so they can use Greptile's learnings to...

64,850 views • 9 days ago •via X (Twitter)

22 Comments

Greptile's profile picture
Greptile9 days ago

Learn more:

Simantak's profile picture
Simantak9 days ago

Yalls dont stop shipping do you. Love it team

Max's profile picture
Max9 days ago

Greptile knowledge base is slept on. It's so powerful having all the context in one place & constantly evolving

Martin Jonsson's profile picture
Martin Jonsson9 days ago

Does it work on historical? Lots of reviews behind me.

Saai Arora's profile picture
Saai Arora9 days ago

Damnnn this is fire

Varik Verilion's profile picture
Varik Verilion9 days ago

Incident history inside the coding loop is a useful addition.

EKOS _ AGI 🦊 🇮🇷's profile picture
EKOS _ AGI 🦊 🇮🇷8 days ago

This is where agent memory starts becoming real infrastructure. The next challenge is making that accumulated knowledge structured, versioned, and traceable — so agents don’t just remember what happened, but understand how that knowledge evolved and where it came from.

Yijie's profile picture
Yijie8 days ago

production quality on this is crazy

cole murray's profile picture
cole murray9 days ago

awesome!

Samuel Hu's profile picture
Samuel Hu9 days ago

the history-of-incidents bit is what i actually want. most mcp demos can answer a file question, but the "why did we do this weird thing" context is the part i keep missing — does it update itself from prs or only docs?

Dominik's profile picture
Dominik9 days ago

the useful boundary is not 'agent can read the codebase.' it is whether each retrieved fact carries provenance, freshness, and an owner. otherwise a knowledge base becomes another prompt-shaped authority with no way to tell stale guidance from a current constraint.

AWE's profile picture
AWE8 days ago

does the incident history get pulled in automatically or does someone still have to write the postmortem

Ali Mirza | AI Agents & Automation's profile picture
Ali Mirza | AI Agents & Automation8 days ago

hooking an mcp incident log directly into the subagent prompt stops it from making the same breaking imports twice.

Bessi's profile picture
Bessi8 days ago

past incidents in the MCP. did not expect that

virtualuncle's profile picture
virtualuncle8 days ago

most codebase context tools tell the agent how things work. knowing how it broke last time is a step past that

Mike Lopez's profile picture
Mike Lopez8 days ago

How do you prevent stale architectural knowledge from becoming authoritative context for the agent?

Mohamed Khlifa's profile picture
Mohamed Khlifa8 days ago

What is the difference between it and things like onsidian git that is free and most common for users ?.

0xdotdot's profile picture
0xdotdot8 days ago

fire

Omair-Inam Abdul-Matin's profile picture
Omair-Inam Abdul-Matin9 days ago

How much will this cost?

Jag's profile picture
Jag9 days ago

Interesting. So all the code base replicates to greptile?

AI Mastery Guide's profile picture
AI Mastery Guide8 days ago

past incidents remembered, that's smart

TonkaToyXL | AI Test Cabin's profile picture
TonkaToyXL | AI Test Cabin8 days ago

This is the missing piece for coding agents. Giving them a living map of the codebase and past incidents is how they stop guessing and start helping for real.

Related Videos