
Perceptdot Sentry
io.github.perceptdotPublished by GitHub account perceptdotv0.1.5Updated Oct 24, 2026
AI agent vision for Sentry error tracking — with ROI measurement. perceptdot.com
Overview
A local MCP server that gives an AI assistant vision into Sentry error tracking, with ROI measurement, according to its registry listing.
- What you can do
- The listing describes AI agent vision for Sentry error tracking, with ROI measurement. No tools are listed in the manifest, so the specific operations an assistant can perform are not documented here. The provider points to perceptdot.com for further detail. Treat the exact capabilities as unverified until you check the package or provider documentation.
- When to use it
- Consider it if you use Sentry for error tracking and want an assistant to work with that error data, or if you want to measure the return on that use. Because the tool list is undocumented, confirm what it actually does before relying on it.
- Requirements
- Runs as a local process over stdio, installed from the npm package @perceptdot/sentry, so it needs Node.js and npm on the user's machine. It is marked desktop only. No authentication, environment variables or headers are declared, but Sentry access would presumably be needed and is not described.
Installation
In SourceWeft
- Open Perceptdot Sentry in the dashboard and add it to a workspace.
- Enable the server for the chats that should use its tools.
Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.
Tools
0Version history
1- v0.1.5LatestSep 16, 2026
Score
25% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
- Reached in the last 30 days25 pts
Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.
- Auth declared10 pts
Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.
- Tools listed15 pts
Answer tools/list without a credential, or ship a package that starts in a sandbox without one.
- DescriptionRequired15 pts
- Logo10 pts
- Documentation15 pts
Declare a GitHub repository with a README, or serve resource_documentation in the OAuth protected-resource metadata.
- License10 pts
Declare a license in the repository or the registry entry.