An MCP server that connects to Vercel API
Nothing to run from here
skillhook is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
90/100
trust score
49
tools declared
local
runs on your machine
—
downloads a day
What it does
Turn this machine into a webhook endpoint that runs Agent Skills with Claude Code or Codex.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user skillhook-mcp '--' npx -y @meterapp/skillhook mcp
# 2 — ask your agent for something these tools do
# skillhook_status, list_skills, get_skill and 46 more
skillhook costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
SKAll 1 server
skillhook1 server
1 category
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. This one runs on your machine: your client starts skillhook as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. Its scan result is on the Security tab — read the surface before you approve it.
Claude Codedeclared by this listing
This is a public server: you run it yourself and this marketplace is not in the path. You need Node.js — the current LTS (24) is the safe choice; npx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user skillhook-mcp '--' npx -y @meterapp/skillhook mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it runs from its publisher’s own package: this marketplace is not in the path, so there is no key of ours to hold and no card to add.
What it writes
One config entry your client uses to start the process locally. A local server runs with your file system and your network, which is why it is priced without metering.
What you approve
49 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Read from its source code. A server that builds its tool list when it starts can list more tools than this.
Overview: home directory, server state, public URL, skills and recent jobs. Call this first.
No parameter schema on file.
Lists every skill with runner, model, auth type, whether its secret is configured, and its webhook URL.
No parameter schema on file.
Returns a skill's summary and the full SKILL.md content.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| name | string | yes | skill name (directory name) |
Creates <home>/skills/<name>/SKILL.md. Writes the instructions (markdown body) and the skillhook frontmatter (runner, model, auth, filters). For bearer/basic/hmac auth a secret is generated and returned once; for provider-signed auth (github, sentry, granola, stripe, slack, linear, svix,…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| name | string | yes | lowercase letters, digits and hyphens |
| description | string | yes | what the skill does and when it runs (1-1024 chars) |
| instructions | string | yes | markdown body: what the agent should do with the payload. Use {{payload}} / {{payload.some.path}} placeholders or let skillhook append the event automatically. |
| runner | string | no | — |
| model | string | no | e.g. opus, sonnet, haiku, claude-opus-5, gpt-5-codex |
| effort | string | no | low|medium|high|xhigh|max |
| auth_type | string | no | default bearer |
| secret_env | string | no | env var holding the secret; default SKILLHOOK_SECRET_<NAME> |
| cwd | string | no | working directory for the agent, e.g. ~/dev/my-repo |
| timeout_seconds | integer | no | — |
| when | array | no | filters, e.g. [{"path":"action","equals":"created"}] |
| env | array | no | env var names from .env to expose to the agent |
| overwrite | boolean | no | — |
Replaces a skill's SKILL.md with new content after validating the frontmatter.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| name | string | yes | — |
| content | string | yes | complete SKILL.md text including frontmatter |
Parses every SKILL.md (or one) and reports errors and missing secrets.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| name | string | no | — |
Runs a skill with a payload through the same prompt, runner and job pipeline as a webhook, skipping HTTP auth, the skill's when filters and de-duplication. Uses the running server when there is one (job visible in its queue), otherwise runs in-process. Set wait_seconds to block for the result;…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| name | string | yes | — |
| payload | no | JSON payload the skill receives (object, array, string…) | |
| headers | object | no | extra request headers to simulate, e.g. {"x-github-event":"issues"} |
| runner | string | no | — |
| model | string | no | — |
| effort | string | no | — |
| wait_seconds | integer | no | default 120 |
Runs the complete text of a SKILL.md (frontmatter included) with a payload, exactly like run_skill, without installing it: the file is kept in the job directory (jobs/<id>/skill/<name>/SKILL.md) and the job has trigger test. Use it to try a draft before create_skill, or to see how a change would…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| skill_md | string | yes | the whole SKILL.md text, frontmatter included; name must be a valid skill name |
| payload | no | — | |
| headers | object | no | — |
| runner | string | no | — |
| model | string | no | — |
| effort | string | no | — |
| cwd | string | no | working directory for the run (default: the skill's cwd, else the copy's own directory inside the job) |
| wait_seconds | integer | no | default 120 |
Signs a payload the way the skill's auth expects and POSTs it to /hooks/<name>, proving the HTTP path (auth, filters, queue) works. Defaults to the local server; set public=true to go through the public URL.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| name | string | yes | — |
| payload | no | — | |
| public | boolean | no | — |
| base_url | string | no | — |
| wait_seconds | integer | no | — |
Recent jobs, newest first. status is how the process ended, outcome whether the task was done. waiting: true lists only the jobs waiting for a person (an unanswered question, or outcome needs_human not yet resumed): answer them with answer_job. after (the next_after of the previous call)…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| skill | string | no | — |
| status | string | no | — |
| outcome | string | no | — |
| trigger | string | no | — |
| failure | no | only jobs that failed this way: auth, usage_limit, rate_limit, budget, max_turns, not_found, timeout, crash, unknown | |
| waiting | boolean | no | — |
| since | string | no | — |
| after | string | no | — |
| limit | integer | no | — |
Every request to /hooks/<skill> the server received, newest first, with its outcome: accepted (a job was created), duplicate, in_flight, skipped (a when filter), rejected (401, 404, 413, 503, …), challenge, error. Use it to see why a webhook did not run. after pages further back.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| skill | string | no | — |
| outcome | string | no | — |
| since | string | no | — |
| after | string | no | — |
| limit | integer | no | — |
Runs a recorded delivery again through the skill as it is now, as a new job with trigger replay: the original payload, headers and query, no signature check, when filters applied unless skip_filters, identical in-flight work is reused when deduplication is enabled on the running server. A…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| force | boolean | no | replay a delivery that was rejected or errored |
Runs the request an earlier job received again, as a new job with trigger replay and replay_of pointing at the original (same payload, headers and query; when filters applied unless skip_filters; runner/model/effort may be overridden).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | yes | — |
| skip_filters | boolean | no | run even when the skill's when conditions do not match the original request |
| runner | string | no | — |
| model | string | no | — |
| effort | string | no | — |
| wait_seconds | integer | no | default 120 |
One delivery record; include_body adds the request body when the log kept it (rejected and filtered deliveries) or the payload of the job an accepted delivery created.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | yes | — |
| include_body | boolean | no | — |
Job record plus optional artifacts (result, response, prompt, stdout, stderr, payload, event) and, when the agent reported any, its progress timeline, pending question and answer.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | yes | — |
| include | array | no | — |
A person's answer to a job that is waiting: delivered live to the agent's pending job_ask_human call when the job is still running (delivered: live); otherwise recorded and, unless resume is never, a new job with trigger resume continues the agent's session with it (claude --resume /…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | yes | — |
| answer | string | no | The answer; may be left out when option or options say it all |
| option | string | no | — |
| options | array | no | — |
| by | string | no | — |
| resume | string | no | — |
| wait_seconds | integer | no | how long to wait for the resume job (default 120; 0 returns at once) |
Cancels a queued or running job on the running server.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | yes | — |
Stores a secret in <home>/.env (mode 600). name is an ENV_VAR_NAME, a skill name (its secret_env) or "admin". Use it for provider signing secrets (Granola whsec_…, Sentry client secret, GitHub webhook secret) and for API keys a skill needs via env:.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| name | string | yes | — |
| value | string | yes | — |
Generates a random secret for a skill (or "admin") and returns it once. Existing secrets are kept unless force=true.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| name | string | yes | — |
| force | boolean | no | — |
Names of secrets in <home>/.env (values are never returned).
No parameter schema on file.
Webhook URL per skill, using the public URL (Tailscale/config) when one exists.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| skill | string | no | — |
mode=funnel: public HTTPS URL (internet). mode=serve: tailnet-only URL. mode=off: disable. mode=status: current exposure. The URL is permanent (your Tailscale node name) and survives reboots.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| mode | string | yes | — |
install: run the server at login (launchd/systemd) and keep it alive. status/restart/uninstall/logs.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| action | string | yes | — |
| lines | integer | no | — |
Whether this machine is paired with Skillhook Cloud (the opt-in dashboard for every machine's webhooks, jobs and health), its URL, machine id and mode (observe: the cloud can look; control: it can also run skills and change the configuration), whether the token is present (never the token itself),…
No parameter schema on file.
Stops the link to Skillhook Cloud: sets cloud.enabled to false, revokes and removes the machine token and key, deletes the local spool, and tells a running server (which stops syncing within seconds). Nothing leaves the machine afterwards. keep_token keeps the token in .env for a later reconnect.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| keep_token | boolean | no | — |
Sends a problem report to the Skillhook team through Skillhook Cloud, from this paired machine (what skillhook cloud report does). Use it only when the person asked to report something, and tell them what goes out (dry_run: true returns exactly that without sending): the title and body (write…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| title | string | yes | — |
| body | string | no | — |
| kind | string | no | default bug |
| severity | string | no | default normal |
| contact_email | string | no | where the Skillhook team answers |
| job_id | string | no | this machine's job id the report is about |
| delivery_id | string | no | — |
| skill | string | no | — |
| diagnostics | boolean | no | attach the machine's facts (default true) |
| dry_run | boolean | no | return the report that would be sent, send nothing |
Checks Node, config, secrets, skills, Claude/Codex login, Tailscale exposure, server and service.
No parameter schema on file.
Everything doctor checks plus, with deep (default), every MCP server Claude Code and Codex know (connected, needs authentication, failed), installed plugins, codex doctor, disk space and each skill's last run, grouped (system, skillhook, runners, tools, skills, exposure). Through the running…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| deep | boolean | no | — |
| refresh | boolean | no | — |
| network | boolean | no | ask the npm registry and probe the public URL (default false through the server, true locally) |
The effective skillhook.json (defaults applied), which keys the running server applies live (hot_keys) and which need a restart (restart_keys: host, port), and what is pending a restart. From the running server when there is one.
No parameter schema on file.
Change skillhook.json: set maps dotted keys to values ({"concurrency": 3, "defaults.model": "sonnet"}), unset lists dotted keys to remove. One validated write; an invalid result changes nothing. The running server re-reads the file at once and says which keys it applied live and which (host,…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| set | object | no | — |
| unset | array | no | — |
Ask the running server to restart: it pauses dispatch while keeping intake and cloud sync available, lets running jobs finish for up to wait_seconds (default 30), then exits only if idle. On timeout it resumes dispatch without terminating jobs; force: true terminates them. Launchd / systemd…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| force | boolean | no | — |
| wait_seconds | integer | no | — |
Ask the npm registry for the newest skillhook (what skillhook update does). With install: true and a newer version, upgrade with the package manager that installed skillhook and restart the background service when it has no jobs in progress; a busy service keeps running the old version until…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| install | boolean | no | — |
Numbers over the jobs and deliveries on this machine: jobs by status, outcome, trigger, runner and failure kind, success and completion rates, duration and queue-wait percentiles, cost and tokens, deliveries by outcome and HTTP status, and the same per skill. since takes 24h, 7d, 2w or an…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| since | string | no | — |
| until | string | no | — |
| skill | string | no | — |
Is each runner (claude, codex, shell) installed and logged in, or given an API key: what every job checks before it starts (a fallback: runner takes over, or the job fails fast with failure.kind auth). Through the running server's cached answer when there is one (refresh probes again).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| refresh | boolean | no | — |
The Claude Code and Codex accounts (named logins) skills run as: for each its state (ready, needs_login, expired, limited, missing_secret, disabled), who it is logged in as, its plan, its usage windows (5h, weekly, per model; with usage: true asked from each account's CLI now), its last use, its…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| usage | boolean | no | — |
| mcp | boolean | no | — |
| refresh | boolean | no | — |
| account | string | no | — |
Repositories whose skillhook.yaml is served by this machine: directory, file, and each hook with its runner, kind (run/skill/prompt), auth, cwd and webhook URL. This is the version-controlled answer to 'which skill runs from which webhook'.
No parameter schema on file.
Registers a repository's skillhook.yaml (dir, or the YAML file itself) in skillhook.json so its hooks are served at /hooks/<name>; the running server picks them up without a restart. With init=true a starter skillhook.yaml is written first when none exists (a run: git pull --ff-only hook for…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| dir | string | yes | repository directory (or path to its skillhook.yaml) |
| init | boolean | no | write a starter skillhook.yaml when the directory has none |
| no_secret | boolean | no | — |
Stops serving a repository's hooks (they answer 404 at once). The repository and its skillhook.yaml are not touched.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| dir | string | yes | — |
Every skill or hook with a schedule:: cron, time zone, catch_up and overlap policy, whether it is enabled and also has a webhook, the next due time, and the last slot, job and status (live from the running server when there is one). A hook with webhook: false runs only on its schedule.
No parameter schema on file.
Bundled example skills (hello, granola-meeting-actions, sentry-triage, …) that add_example can copy.
No parameter schema on file.
Copies a bundled example into <home>/skills (optionally under another name) and generates its secret when skillhook manages it.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| name | string | yes | — |
| as | string | no | — |
Tell skillhook (and the people watching) what you are doing right now (Markdown). state is working (default) or blocked; percent 0-100 and step are optional. title names the whole job in a few words ("Fix the 500 on /api/sync") and stays until a later report changes it: give it in the…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| message | string | yes | — |
| title | string | no | — |
| state | string | no | — |
| percent | number | no | — |
| step | string | no | — |
Ask a person a question (Markdown) and wait for the answer (up to wait_seconds, default …). Give the options when there are a few (buttons on Skillhook Cloud's inbox; recommended marks the one you suggest, multiple lets them pick several), and in context what they need to know to decide (a diff,…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| question | string | yes | — |
| context | string | no | — |
| wait_seconds | integer | no | — |
Record the task outcome for the people who follow this job: headline (the result in one line), summary (one paragraph, Markdown: what was done, what was found, what remains, how to check it), title (what the job was about, when job_progress did not name it), links (what started the run as kind…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| outcome | string | yes | — |
| headline | string | no | — |
| summary | string | yes | — |
| title | string | no | — |
| links | array | no | — |
| data | no | — |
Add a line to the job's timeline without changing its state (a finding, a decision, a link).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| text | string | yes | — |
What this run is: job id and directory, skill, trigger, the payload and event files, what was reported so far and any earlier question and answer (useful when the session was resumed).
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
Free
$0 forever
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source published under MIT
- Runs on your machine — nothing of it reaches our gateway
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install skillhook or to call it, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: —
ATrust score 90 / 100
Release 0.15.0 · scanned 4 Nov 2026
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
Threat score100
Client score90
Findings12 threat · 5 capability
Capabilitycritical
Coveragesource
Verificationsource
Surface digest4967889db13cb0d1dd86c89d9a8805e961f58650135d72db7a7bad96571758fa
Score vectorthreat 100 → client 90
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | critical | capability blast radius (critical) — client exposure if the model is manipulated | −10 |
| verification-discount | source | publisher verification (provenance) — cryptographic build provenance ties the artifact to its source | −0 |
| coverage-honesty | source | inspection depth (source) — how much of the target the scan could see | −0 |
score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
Tool surfaceread
Implementation sourceread
Package metadataread
Live transportnot available
Tools were statically extracted from the published source (49 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
3 of the 49 recovered tools are registered only when connected is false (dist/cloud/bridge.js:112) — typically when a key or option is configured. They are part of the server's surface and were analysed; a server started without that configuration exposes only the other 46.
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. critical is the level these add up to.
46 tools are registered unconditionally · 3 more only when connected is false (dist/cloud/bridge.js:112) — typically when a key or option is configured. All 49 are in the table below and were analysed; the conditional ones are marked.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| generate_secret | external-sink | external-sink: keyword "webhook", declares readOnlyHint: false, destructiveHint: true, openWorldHint: true |
| get_pricing conditional | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| create_checkout_link conditional | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| skillhook_cloud_setup conditional | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| job_progress | no tags | |
| job_ask_human | no tags | |
| job_set_outcome | no tags | |
| job_note | no tags | |
| job_context | no tags | |
| skillhook_status | no tags | |
| list_skills | no tags | |
| get_skill | no tags | |
| create_skill | no tags | |
| update_skill_file | no tags | |
| validate_skills | no tags | |
| run_skill | no tags | |
| test_skill | no tags | |
| send_test_webhook | external-sink | external-sink: keyword "webhook" |
| list_jobs | no tags | |
| list_deliveries | no tags | |
| replay_delivery | no tags | |
| replay_job | no tags | |
| get_delivery | no tags | |
| get_job | no tags | |
| answer_job | no tags | |
| cancel_job | no tags | |
| set_secret | external-sink | external-sink: keyword "webhook" |
| list_secrets | sensitive-source | sensitive-source: keyword "list_secrets" |
| get_webhook_urls | no tags | |
| expose | no tags | |
| service | no tags | |
| cloud_status | no tags | |
| cloud_disconnect | no tags | |
| cloud_report_issue | no tags | |
| doctor | no tags | |
| get_health | no tags | |
| get_config | no tags | |
| update_config | no tags | |
| restart_server | no tags | |
| check_update | no tags | |
| get_stats | no tags | |
| get_runners | no tags | |
| list_accounts | no tags | |
| list_projects | no tags | |
| link_project | no tags | |
| unlink_project | file-write | file-write: keyword "unlink" in tool name |
| list_schedules | no tags | |
| list_examples | no tags | |
| add_example | no tags |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
create_checkout_link → list_secrets → generate_secret
A cross-tool exfiltration chain exists: create_checkout_link → list_secrets → generate_secret.
Supply chain and provenance
Integrityfirst-seen
Surface digest4967889db13cb0d1
Scanned2026-11-04
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
Always latest — the install command names no version, so it installs the newest release when it runs; the current release on file is 0.15.0. Pin a release below and the command asks for exactly that one.
0.15.0
4 Nov 2026
latestNo release note was published with this version.
0.14.7
undated
- The version this listing was on when mcprush began following its releases. The registry was not asked when it shipped, so this row carries no date.
—
no reviews yet
Who can review
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Sign in to write one
Any signed-in account that does not publish skillhook can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.