Built-in WildEdge.dev connector

Open
#63 0 comments 0 reactions 0 assignees View on GitHub

Maintainers usually reply within 1 day

Nobody has claimed this yet.

Assessment

Difficulty
5/5
Estimated time
Over a week
Newbie friendliness
35/100
Issue type
Feature
Clarity
Mostly clear
Activity status
Active
Tech stack
python

Research direction

Read the existing Sentry connector and its SENTRY_MCP_TOOLS allowlist to understand how built-in connections and read-only tools are registered. Then trace how production-error-review consumes connector data and run it against a test app with one new failing event; done means the report names that event and links its run trace, with the requested token scope and query limits enforced.

Written by the indexing model from the issue text.

Description

area: connectors help wanted idea

Idea

Add WildEdge.dev as a built-in connection, next to the existing Sentry connector, using WildEdge's MCP server.

Problem

monitoring-coverage-review and production-error-review need events, run traces, alerts and dashboards for the apps they review. Today only Sentry covers this, so teams that use WildEdge.dev for observability have to set up a custom connection.

Proposed initial scope

  • A WildEdge.dev connection with a scoped, read-only token, limited to one company and the chosen apps.
  • Read tools only, as an allowlist like SENTRY_MCP_TOOLS: list apps, list and get events, get a run trace, list and get notifications, get dashboard data, and SQL queries over the event schema.
  • No write tools (resolving notifications, creating apps, dashboards or keys, managing members).
  • Query size and time-range limits, so a model can't pull unbounded data through SQL or event listing.

Validation

Run production-error-review against a test app that has one new failing event and confirm the report names it and links its run trace.

Dominant language
Python
Stars
1
Forks
1
Avg merge
1h 9m
Merged PRs (30d)
322

Getting set up

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

More from piotrekno1/second-shift

All issues in piotrekno1/second-shift

Similar issues

More Python issues

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.