Codecov + Memtro

Ask Codecov whether a pull request lowered coverage, and in which files.

Connect Codecov with a personal access token, your git service and owner, and Memtro reads the coverage of the owner's repositories, coverage per commit and per pull request with whether CI passed, a pull request's coverage change by file, and the lowest-covered files on a branch. The token is your own, so Memtro sees the repositories you can see in Codecov. Only codecov.io is supported. It reads on demand and there is no hourly sync. Nothing is written to Codecov.

In Memtro

What you can do with Codecov in Memtro

Ask in plain English from chat, your editor, a scheduled job or your own agent. The model picks the right Codecov tool, reads what it needs, and answers with the source cited.

Reads

  1. 01Repositories of the connected owner with coverage percent, language, default branch and last update
  2. 02One repository's coverage at a branch head or commit, with its lowest-covered files
  3. 03Coverage narrowed to files under a path or to one coverage flag
  4. 04Recent commits with coverage, lines missed, whether CI passed and the author
  5. 05Pull requests with base and head coverage, the change, patch coverage and CI result
  6. 06A pull request's changed files with their coverage before and after
In practice

Ask it like you would a colleague

Once Codecov is connected, these are the kinds of things people ask. Plain questions, no syntax. If the answer lives partly in another system you have connected, Memtro looks there too.

Codecov + Memtro
  • Did pull request 42 lower coverage, and where?

  • Which repositories have the lowest coverage?

  • Which files on main have the lowest coverage?

  • What was coverage on the last commit to the release branch?

  • Which open pull requests dropped coverage this week?

01

Reviewing a pull request

A reviewer at Acme asks whether pull request 42 on the billing service lowered coverage. Memtro reads the comparison: head coverage fell from 81.4% to 79.9%, patch coverage is 52%, and most of the drop is in two invoice files.

02

Where tests are thin

The engineering lead asks which Northwind repositories have the lowest coverage. Memtro lists them with their coverage and when it was last updated, then reads the weakest repository's default branch and names the five files with the least coverage.

Teams

Where it fits

The teams that lean on Codecov most, a question each of them asks, and what they connect beside it.

Better together

Works with

A record in Codecov is rarely the whole story. Connect the systems that hold the rest and Memtro checks them together, then remembers what it learned so the next question starts further along.

Also in Engineering and operations

Using something else for the same job, or both? Each connector has its own tools; connect as many as you like.

Setup

How to connect

Connect withPersonal access token, git service and owner
  1. 1

    In Codecov open your avatar → Settings → Access, generate a token and copy it. It is your own, so Memtro sees the repositories you can see

  2. 2

    In Connections → Codecov in Memtro paste the token, set Git service to where the code lives (github, github_enterprise, gitlab, gitlab_enterprise, bitbucket or bitbucket_server) and Owner to the name in its Codecov address, such as acme in app.codecov.io/gh/acme

  3. 3

    Connect. Only codecov.io is supported: self-hosted Codecov has no documented API address

  4. 4

    Ask whether pull request 42 lowered coverage, and where

Also works from

Chat in the dashboard, the OpenAI-compatible API, scheduled jobs, and any MCP client: Claude Code, OpenCode, Cursor, Claude Desktop. The Codecov tools are the same everywhere.

FAQ

Questions

Can Memtro change anything in Codecov?+

Not yet. Today every Codecov tool reads, searches or lists. When the connector gains actions, each is marked, granted by name per team and used only when a person asks for exactly that, so nothing is created, sent, updated or deleted until you say so.

Who can use a Codecov connection?+

A personal connection serves only your own requests. A shared connection serves the organisation: everyone, or only the teams an admin chooses. Admins can always add shared connections; other members need the permission.

Does Memtro store my Codecov data?+

Credentials are encrypted at rest. Tool results are cached briefly so agent loops do not repeat identical calls, and the facts the model extracts are saved to your organisation's memory with provenance (system, record and link) so they can be checked and superseded.

How do I connect Codecov?+

Personal access token, git service and owner. In Codecov open your avatar → Settings → Access, generate a token and copy it. It is your own, so Memtro sees the repositories you can see.

Connect Codecov in a few minutes

Seven-day free trial, then one monthly price per organisation. Connectors, jobs and memory are never metered.

Where agents remember your company

Sign in, add a provider key, create an API key and point your tools at Memtro. It takes about five minutes.

7-day free trial · card on file, nothing charged until it ends · cancel any time