# Edge (npm · @getedge/mcp)

Gives your agent the right public skill for each task and loads it on demand.

- Trust score: 65/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-17

## Components

- npm · `@getedge/mcp`: 65/100 (this document), [markdown](https://verifymcp.io/servers/getedgehq-edge/getedge-mcp.md), [page](https://verifymcp.io/servers/getedgehq-edge/getedge-mcp)

## Channel facts

- Registry: `npm`
- Package: `@getedge/mcp`
- Version: `0.6.25`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-10-17.

- **Supply Chain Security**: 100/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - No install/post-install scripts declared.
  - No production dependencies, so there is no dependency health to assess.
- **Provenance & Transparency**: 19/100
  - Repository check failed: no source repository is declared.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 0 days ago).
  - Security-disclosure policy not yet verified: we couldn't inspect the source repository.
- **Schema Quality & AI Usability**: 63/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 3139 tokens (~285/item across 11 items; 11 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 13/100
  - Stability observed for 4 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 99/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 98% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 11 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 12 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the Edge MCP server?

Edge runs locally as an npm package, launched with npx -y @getedge/mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add getedgehq-edge -- npx -y @getedge/mcp
```

### Cursor

```json
{
  "mcpServers": {
    "getedgehq-edge": {
      "command": "npx",
      "args": [
        "-y",
        "@getedge/mcp"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "getedgehq-edge": {
      "command": "npx",
      "args": [
        "-y",
        "@getedge/mcp"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add getedgehq-edge -- npx -y @getedge/mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "getedgehq-edge": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "@getedge/mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add getedgehq-edge --command npx --arg -y --arg @getedge/mcp
```

### Hermes

```yaml
mcp_servers:
  getedgehq-edge:
    command: "npx"
    args: ["-y", "@getedge/mcp"]
```

### Netclaw

```json
{
  "McpServers": {
    "getedgehq-edge": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "@getedge/mcp"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add getedgehq-edge -t stdio -c npx -a -y @getedge/mcp
```

### Other

```json
{
  "mcpServers": {
    "getedgehq-edge": {
      "command": "npx",
      "args": [
        "-y",
        "@getedge/mcp"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-10-17 (score 65, +1)

No change was recorded against any check on this day. Stability & Change Management went from 10 to 13. That category is still filling its 30-day observation window: 3 days of observed history at the previous scan, 4 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-16 (score 64, +1)

- [security regression] Tool safety: pass → unverified
- [security] Stability: Stability not yet verified: we do not have a sandbox capture of the MCP schema this version of the package serves yet.
- [functional regression] Capabilities: pass → unverified
- [functional regression] Tool coverage: 100 → unverified
- [functional improvement] Schema quality: 343 → 285
- [functional improvement] Stability: unverified → 0.10
- [functional] Package version: 0.6.21 → 0.6.25

### 2026-10-13 (score 63, +29)

- [security improvement] Injection markers: unverified → pass
- [security] First check of Judged manipulation: pass
- [security] Stability: Stability not yet verified: not enough scan history yet (needs a 30-day window).
- [functional improvement] Tool coverage: unverified → 100
- [functional improvement] MCP protocol: unverified → pass
- [functional] First check of Schema quality: fail
- [functional] First check of Schema quality: excellent
- [functional] First check of Destructive annotations: pass
- [functional] First check of Schema quality: fail
- [functional] First check of Tool coverage: 98

### 2026-10-11 (score 34)

First indexed and scored.

## MCP tools (11)

### `find_skill` (~297 tokens)

Edge Skills: find an expert skill

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 work in a named framework, API or file format. This counts even if the task seems routine. Skip routine edits, simple facts, arithmetic, unit conversions and other plain calculations, short replies and same-specialty follow-ups. Honor explicit no-Edge requests. Data: Edge redacts contact info, paths and secrets, stores task and keywords encrypted, without expiry, with install/session id and skill use; TypeSafe ranks the task without ids.

Input parameters:

- `keywords` (string): keywords: the 2-6 words a skill for this would be named with, e.g. "postgres migration"; your own rephrasing of the task goes here, not in query
- `query` (string, required): the user's request in their own words: copy it verbatim (up to about three sentences); do not paraphrase, generalise or shorten it. Leave out file contents and secrets; Edge removes contact details,…
- `selected_skill` (string): Only when the user explicitly chose a catalog skill: its exact Skill slug. Pair with selected_source.
- `selected_source` (string): Only when the user explicitly chose a catalog skill: its exact Source (owner/repository). Pair with selected_skill.

### `use_skill` (~295 tokens)

Edge Skills: load skill

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 that fail its security gate. Loading is temporary and never installs anything permanently. For an oversized result, pass file and the original request_id to fetch one named file from the same scanned version; pass page for more content. Read the third-party instructions and any commands before following them, then continue the original task.

Input parameters:

- `file` (string): Fetch one named file from the same pinned, scanned mirror bundle; reuse the original request_id
- `page` (integer): Zero-based page of a named file, for files too large for one tool result
- `request_id` (string): The request_id printed by the find_skill result this candidate came from, so the selection can be attributed to its search
- `skill` (string, required): The Skill printed by find_skill. A short name is matched against this session's last search
- `source` (string): The candidate Source printed by find_skill, usually owner/repository
- `task_label` (string): Optional: a short generic name for the user's task, 3-8 words, for example "Build a quarterly revenue report". Shown on the user's private Edge page. Never the user's request text; no names, emails,…

### `rate_skill` (~821 tokens)

Edge Skills: rate a loaded skill

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 the deliverable, once; if its result gives an Edge closing line, end your answer with it. Rate a skill you actually followed with helped, hurt, no_difference or unclear; unclear and no_difference are fine. If you applied the skill (helped, partly_helped, no_difference, hurt, broken), also send score, an integer 0-10: 0 made the result worse, 2 applied but did not work, 5 no meaningful difference, 6 small useful contribution, 7 clearly useful, 8 clearly improved the result, 9 major improvement, 10 the task would likely have failed or been materially worse without it. A failure is a low score, not a skipped rating. Omit score for wrong_skill, loaded_not_used and unclear. Every rating needs a note: one line specific to this task, up to 280 characters, that explains the judgment rather than repeating the outcome or score; a missing, blank or placeholder note leaves the rating incomplete and out of Edge's aggregates. Judge the outcome yourself; never ask the user. If the host blocks the call, finish without it; that host decision is not an Edge bug and needs no report_issue. The server identifies the skill from this request_id. Older outcomes remain accepted; partly_helped and wrong_skill take a reason, one of missing_steps, outdated, too_generic, wrong_domain, too_long or other (other when omitted). Notes over 280 characters are cut. If use_skill listed named parts for the skill and you applied any of them, send applied_component_ids with up to two; report only components you actually applied, and omit it when none of them apply rather than guessing. Keep the note free of the user's query, code, names and private data. With a Pro key, once the task is done and the skill was applied, you may include task: one UUID per logical task (reuse it for every sk…

Input parameters:

- `applied_component_ids` (array): Up to two ids from the skill's named parts listed in the use_skill result, only parts you actually applied in this task; send them whenever you applied any. Omit when none were listed or none were ap…
- `note` (string): Required for every rating: one line specific to this task on why (up to 280 characters; a longer note is cut) that explains the judgment, not a restatement of the outcome or score. A missing or place…
- `outcome` (string, required): Once the task's outcome is known: helped, hurt, no_difference or unclear. Only for a skill you actually followed.
- `reason` (string): For partly_helped or wrong_skill: missing_steps, outdated, too_generic, wrong_domain, too_long or other. Defaults to other; free text becomes other.
- `request_id` (string, required)
- `score`: Integer 0-10 when you applied the skill (helped, partly_helped, no_difference, hurt, broken); omit for wrong_skill, loaded_not_used and unclear. 0 made it worse, 2 did not work, 5 no difference, 7 cl…
- `task` (object): Optional completed-task report, separate from legacy skill feedback. Pro key required. One report per logical task; revision replaces the prior report. Only report actual application.

### `report_issue` (~205 tokens)

Edge Skills: report an Edge issue

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 approval denial is not an Edge failure; skip the blocked call and do not report it as an Edge bug. For how well a loaded skill did on the task, use rate_skill instead. Describe what happened without secrets or private user data. Include contact only if the user explicitly gave an email for this.

Input parameters:

- `contact` (string): An email to reply to, only if the user explicitly gave it for this report
- `kind` (string, required): bug, wrong_skill, setup, or idea
- `message` (string, required): What happened or what you suggest, at most 2000 characters. No secrets or private user data.
- `request_id` (string): The request_id of the Edge call this is about, if any

### `feedback` (~141 tokens)

Edge Skills: send Edge feedback

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.

Input parameters:

- `contact` (string): An email to reply to, only if the user explicitly gave it for this report
- `kind` (string, required): bug, wrong_skill, setup, or idea
- `message` (string, required): What happened or what you suggest, at most 2000 characters. No secrets or private user data.
- `request_id` (string): The request_id of the Edge call this is about, if any

### `scan_skill` (~277 tokens)

Edge Skills: skill security audits

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 findings, date, and the serve or withhold decision. For a local skill (local: a folder, SKILL.md path, or installed name), Edge runs its offline checks on this machine; nothing is uploaded. Set share_with_snyk=true only if the user explicitly agreed to send that local skill's files, hostname, and username to Snyk Agent Scan. Relay the Result line and findings; automated checks are not a guarantee.

Input parameters:

- `local` (string): Local skill: path to its folder or SKILL.md, or the name of an installed skill. Scanned on this machine; do not combine with source/skill
- `share_with_snyk` (boolean): Local skill only. true only if the user explicitly agreed to send the skill's files (plus this machine's hostname and username) to Snyk Agent Scan. Default false: nothing is uploaded
- `skill` (string): Catalog skill: the Skill printed by find_skill (owner/repository@skill also works)
- `source` (string): Catalog skill: the Source printed by find_skill, usually owner/repository

### `my_activity` (~85 tokens)

Edge Skills: open my Edge page

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. Never call it on your own initiative, never open the link yourself, and never put it in files, commits, issues or shared documents.

### `star_skill` (~172 tokens)

Edge Skills: star a skill

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 it fits a task, and never shown when it does not. Pass the Source and Skill that find_skill printed; set starred to false to unstar. Never call it on your own initiative. Reply with the returned line.

Input parameters:

- `skill` (string, required): The Skill printed by find_skill
- `source` (string): The Source printed by find_skill, usually owner/repository. Leave it out only when the skill was in this session's last find_skill result
- `starred` (boolean): true (the default) stars the skill; false unstars it

### `list_starred` (~62 tokens)

Edge Skills: list my starred skills

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 it on your own initiative.

### `health` (~64 tokens)

Edge Skills: check Edge health

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 relying on Edge after a long pause. It sends no task content.

### `benchmark` (~533 tokens)

Edge Skills: benchmark skills on your tasks

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 skill to compare it against no skill; pass several to rank them all against no skill on the same leaderboard (mean, 95% CI, paired lift vs no-skill, runs, tokens, time). Skills are Edge catalog references (owner/repo@skill) or local skill paths. Tasks come from the user (inline or a JSONL task file), or from a category so Edge suggests one by default; use task_count=3 when the user asks for three. NEVER runs immediately: the first call returns the plan, its cost (tasks × conditions × runs) and a confirmation token; show the plan to the user, and only after an explicit yes call again with the same arguments and that confirmation_token. Results stay on this machine under ~/.config/edge/evals/; only scores, category, skill ids, run counts and agent/model are shared with Edge.

Input parameters:

- `agent` (string): Local agent CLI to spawn; defaults to whichever is installed
- `category` (string): A task category (e.g. security-review) so Edge suggests one task by default for the user to review
- `confirm` (boolean): Not enough on its own: running needs confirmation_token from a plan the user approved.
- `confirmation_token` (string): The confirmation token printed by the plan call. Pass it only after showing that plan to the user and getting an explicit yes; it runs exactly that plan, once.
- `model` (string): Model override for the local CLI; defaults to the CLI's configured model
- `runs` (integer): Repetitions per task and condition (default 1 for a single skill, 2 when comparing several)
- `skills` (array, required): Skills to evaluate; each is 'none', an Edge catalog reference like owner/repo@skill, or a local path to a skill directory or SKILL.md. A no-skill baseline condition is added automatically.
- `task_count` (number): For category suggestions only: one task by default, or three when the user asks for more evidence
- `task_file` (string): Path to a JSONL task file (one task per line, same shape as inline tasks)
- `tasks` (array): Inline tasks, each with a grader. Use for the user's real task.
- `timeout_ms` (integer): Per-task limit in ms (default 600000 = 10 min)

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/getedgehq-edge/getedge-mcp#diagnostics

## Score history

- 2026-10-17: 65
- 2026-10-16: 64
- 2026-10-15: 63
- 2026-10-14: 63
- 2026-10-13: 63
- 2026-10-12: 34
- 2026-10-11: 34

## Common questions

### What is the Edge MCP server?

Edge is an MCP server listed in the public MCP registry as io.github.getedgehq/edge. Gives your agent the right public skill for each task and loads it on demand. This page covers its npm package (@getedge/mcp).

### Is the Edge MCP server safe to use?

Edge scores 65 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 17 October 2026. It declares no install or post-install scripts. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the Edge MCP server expose?

Edge exposes 11 tools: find_skill, use_skill, rate_skill, report_issue, feedback, and 6 more. Their descriptions and schemas cost roughly 2,952 tokens of context every time the server is loaded.

### Is the Edge MCP server still maintained?

Edge is still listed as active in the MCP registry. We last reached this channel on 17 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What licence is the Edge MCP server under?

Edge declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

## Links

- npm package: https://www.npmjs.com/package/@getedge/mcp
- Socket report: https://socket.dev/npm/package/@getedge/mcp
- Website: https://getedge.cc/
- Changelog RSS feed: https://verifymcp.io/servers/getedgehq-edge/getedge-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/getedgehq-edge/getedge-mcp.json
- HTML version of this page: https://verifymcp.io/servers/getedgehq-edge/getedge-mcp