# io.github.blinkboxhq/blinkbox

Open-source Zapier/n8n alternative as an MCP server: agents build, run and debug your workflows.

- **Type:** MCP server
- **Trust:** 60/100 (B), scored on the content rubric
- **Verification:** community-indexed — nobody has claimed this listing
- **Version:** 1.0.0
- **Author:** io.github.blinkboxhq
- **License:** Unknown
- **Endpoints:** streamable-http https://mcp.blinkbox.net/mcp
- **Source:** https://github.com/blinkboxhq/Blinkbox
- **Endpoint health:** reachable (last checked 2026-09-16T16:49:52.591Z, 1 sample) — uptime is not a security property and is not part of the trust score
- **Compatible clients:** claude-code, cursor, copilot, chatgpt, gemini (basis: transport)

## Trust

60/100 (B), scored on the content rubric
- Publisher verified: no
- Install scripts: nothing suspicious found
- Prompt-injection scan: clean
- Obfuscation scan: clean
- Evidence age: 1 day

## Security scan

- **Status:** clean
- **Scanned:** 2026-09-16T16:49:43.503Z
- **Version scanned:** HEAD
- **CVEs:** no coverage — this entry has no package coordinates to query OSV against, so "no known CVEs" is NOT asserted for it.

## Tools

22 declared. Statically extracted from the shipped source — a floor on the surface, not a census.
- `create_workflow` — Create a BlinkBox automation workflow with fully configured nodes. REQUIREMENT: every node config must be production-ready — real field values, real prompts, re
- `ask_user` — Ask targeted clarifying questions when the request is genuinely ambiguous or when building an AI agent. AI-agent requests should use a 5-point build brief: goal
- `create_file` — Create a file and send it to the user as a download. Use this whenever producing code, documents, CSV/JSON data, reports, or any file the user would want to sav
- `blinkbox`
- `list_automations` — List the user's Blinkbox automations (workflows) with their on/off status, trigger, and id.
- `get_automation` — Get full details of one automation by name or id: status, trigger, and its steps.
- `run_automation` — Run an automation now by name or id (works whether it's active or not). Optionally pass input data. Returns the execution id.
- `get_execution` — Check the status and result of a workflow run by its execution id.
- `get_execution_logs` — Get the step-by-step logs for a workflow run by execution id.
- `list_executions` — List recent runs of an automation (by name or id) with their statuses.
- `activate_automation` — Turn an automation ON (by name or id) so its trigger runs it automatically. The workflow is validated first; if it's incomplete this returns why.
- `deactivate_automation` — Turn an automation OFF (by name or id) so it stops running automatically.
- `rename_automation` — Rename an automation (look it up by current name or id).
- `delete_automation` — Permanently delete an automation by name or id. This cannot be undone.
- `list_nodes` — Browse or search Blinkbox's node catalog — the building blocks of a workflow. Only nodes the user can actually reach from a picker are listed, so anything retur
- `get_node` — Get everything needed to configure one node: its config fields (key, type, whether it's required, an example value, what it means), the output fields later step
- `list_node_actions` — List the operations an app node can perform — e.g. slack → send_message, list_channels — with what each one does, the OAuth scopes it needs, and which is the de
- `list_credentials` — List the user's saved credentials by name, type and id. Secrets are never returned.
- `create_credential` — Save a new credential so nodes can authenticate. Use this for API-key / token style credentials — pass a name and the secret value.
- `create_automation` — Build a brand-new automation from a plain-English description using Blinkbox's AI builder. Example: 'When a Stripe payment succeeds, send me a Slack DM'. Option
- `blinkbox_api_get` — Read ANY Blinkbox REST endpoint the user owns (GET only). Use this for every read the named tools above don't already cover — analytics, profile, workspace memb
- `blinkbox_api` — Full control of Blinkbox: call ANY Blinkbox REST endpoint the user owns, with any HTTP method. For plain reads prefer blinkbox_api_get, which needs no approval.

## Install

**Verdict: review** — Installable, but 2 things to check first: No CVE coverage: this entry has no npm/PyPI coordinates to query OSV against, so "no known vulnerabilities" is not a claim that can be made about it.
**Cautions** (coverage gaps and advisories — never blocking)
- No CVE coverage: this entry has no npm/PyPI coordinates to query OSV against, so "no known vulnerabilities" is not a claim that can be made about it.
- No publisher has proved control of this listing; it is indexed, not vouched for.
**Config** (claude-code):
```json
"{\n  \"mcpServers\": {\n    \"blinkbox\": {\n      \"type\": \"http\",\n      \"url\": \"https://mcp.blinkbox.net/mcp\"\n    }\n  }\n}"
```

## Blast radius

Moderate to extensive — no credential declaration found, from the publisher, the upstream registry, or the README. Known so far: deletes data; runs on someone else's infrastructure.
- Floor 33, ceiling 57 (tier: unknown)
- `unknown` means the floor and ceiling land in different bands — not measured enough to name one. It does not mean low.
- This is impact, not likelihood. A high radius is not a defect: a filesystem server is supposed to write files. It is never part of the trust score.

## Machine-readable views of this entry

- Signed JSON: https://forgeregistry.com/api/v1/packages/io.github.blinkboxhq%2Fblinkbox
- Install plan: https://forgeregistry.com/api/v1/packages/io.github.blinkboxhq%2Fblinkbox/install-plan
- Alternatives: https://forgeregistry.com/api/v1/alternatives/io.github.blinkboxhq%2Fblinkbox
- HTML page: https://forgeregistry.com/registry/io.github.blinkboxhq%2Fblinkbox
- MCP: POST https://forgeregistry.com/api/mcp → `forge_get_package` / `forge_install_plan`

## About this document

Generated by Forge (https://forgeregistry.com) — a compact rendering of the same record served, signed, at the JSON URL above. Trust and scan facts are the registry's own measurements; anything Forge did not measure is named as unmeasured rather than omitted.