io.github.getedgehq/edge · version 0.6.49 · 2,160 weekly npm downloads · audited 2026-11-03
Notes
No hidden-instruction or invisible-character findings in any tool, prompt, or resource description.
Checks the directory's published tool requirements that are visible from tools/list. Passing them does not guarantee acceptance.
| Name | Title | Hint | Description |
|---|---|---|---|
find_skill | Edge Skills: find an expert skill | read-only | Use Edge first when the user asks for a specialist deliverable: slides, documents, spreadsheets, UI or visual design, data analysis, charts, video or media, a security review, research methods, scientific computing, or w… |
use_skill | Edge Skills: load skill | read-only | Load a selected skill returned by find_skill for this task. Edge searches ~130k public skills from its index of the skills.sh catalog, screens results against available independent scanner audits, and withholds skills th… |
rate_skill | Edge Skills: rate a loaded skill | writes | Records only an Edge rating of a skill you used: it does not change the user's files or task output and takes no action outside Edge. Retries with the same request_id never add a second rating. Rate only after completing… |
report_issue | Edge Skills: report an Edge issue | writes | Report a bug or idea about Edge itself: an Edge call that failed or answered wrongly, a skill suggestion that did not fit, setup trouble, or a feature idea. You may call this on your own when an Edge call fails. A host a… |
feedback | Edge Skills: send Edge feedback | writes | Deprecated: the old name of report_issue, kept so older setups keep working. Call report_issue instead; this does exactly the same thing (report a bug or idea about Edge itself). A host approval denial is not an Edge bug… |
scan_skill | Edge Skills: skill security audits | read-only | Check a skill's security before using or installing it. For a catalog skill (source + skill as find_skill printed them), Edge checks the catalog bundle before load or reuses a current exact-bundle audit, then shows findi… |
my_activity | Edge Skills: open my Edge page | writes | Only when the user asks to open or see their Edge page or Edge activity (for example "open my Edge page"): returns a private one-time link to it, single use, valid for 10 minutes. Reply with the returned line exactly. Ne… |
star_skill | Edge Skills: star a skill | writes | Only when the user asks to star, favourite or save a skill (for example "star this skill", "save this one", "unstar it"): stars or unstars that skill for this user. A starred skill is ranked first by find_skill whenever … |
list_starred | Edge Skills: list my starred skills | read-only | Only when the user asks to see their starred, favourite or saved skills (for example "show my starred skills"): lists them with source, a one-line description and the skill's getedge.cc page when it has one. Never call i… |
manage_collection | Edge Skills: follow a collection | writes | Only when the user asks to follow, unfollow or list Edge collections (for example "follow collection federico/comms", "follow this collection" with a getedge.cc/collections/ link, "show my collections"): a collection is … |
find_tool | Edge Skills: find a live data tool (beta) | read-only | BETA. Live data tools through Edge. Free: startup jobs and hiring (which startups are hiring, open roles, jobs in a city or remote, jobs at seed/Series A startups or in an investor's portfolio (a16z, Index...), companies… |
use_tool | Edge Skills: run a live data tool (beta) | read-only | BETA. Run a read-only Edge data tool. For startup jobs (free) call it directly with tool "rocketlist.search_jobs" and input like {"query":"engineer","city":["Berlin"],"stage":["Seed"]} (title, company, stage, location, s… |
health | Edge Skills: check Edge health | read-only | Check whether Edge works in this session: connection, Edge backend, Pro key and installed-skill index, each reported separately. Call it when Edge seems unavailable, when the user asks about Edge's status, or before rely… |
benchmark | Edge Skills: benchmark skills on your tasks | writes | Measure whether skills actually help on real tasks: runs the tasks with each given skill and with no skill, using the local claude or codex CLI subscription, then grades every run blindly with the task's grader. Pass one… |
npx mcpvetter scan --liveAdd this to a README:
[](https://mcpvetter.com/servers/getedge-mcp)Get the MCPVetter verified badge, a re-audit within 24 hours of every npm release, and an email whenever tools, findings, or Claude directory readiness change. $29 per server per month. You prove ownership first, free.