WorkflowsBLOCK
Store, query, and create YAML workflow playbooks for LLM agents via MCP. STDIO or Streamable HTTP.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
@cyanheads/workflows-mcp-server Store, query, and create YAML workflow playbooks for LLM agents via MCP. STDIO or Streamable HTTP. 5 Tools
[](./CHANGELOG.md) [](./LICENSE) [](https://github.com/users/cyanheads/packages/container/package/workflows-mcp-server) [](https://modelcontextprotocol.io/) [](https://www.npmjs.com/package/@cyanheads/workflows-mcp-server) [](https://www.typescriptlang.org/) [](https://bun.sh/)
[](https://github.com/cyanheads/workflows-mcp-server/releases/latest/download/workflows-mcp-server.mcpb) [](https://cursor.com/en/install-mcp?name=workflows-mcp-server&config=eyJjb21tYW5kIjoibnB4IiwiYXJncyI6WyIteSIsIkBjeWFuaGVhZHMvd29ya2Zsb3dzLW1jcC1zZXJ2ZXIiXX0=) [](https://vscode.dev/redirect?url=vscode:mcp/install?%7B%22name%22%3A%22workflows-mcp-server%22%2C%22command%22%3A%22npx%22%2C%22args%22%3A%5B%22-y%22%2C%22%40cyanheads%2Fworkflows-mcp-server%22%5
616f6f04c9d4OBSERVED · 2026-10-08Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control.
claude mcp add workflows-mcp-server -- npx -y @cyanheads/[email protected]
claude mcp add workflows-mcp-server -- npx -y @cyanheads/[email protected]
Exposed tools (2)
1 read · 0 write · 1 destructive. Blast radius: 1 tool can delete or overwrite — an agent that can be talked into calling a tool can be talked into calling this one.
| Tool | Risk | Description |
|---|---|---|
multi-del | destructive | multi version delete |
multi-ver-wf | read | Multi-version test |
Trust audit
BLOCKgrade F · trust 47/100 Do not install this without reading the findings. The audit found something that could harm you or your machine.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | FAIL |
| L2 | Instruction surface (what it tells the agent) | FAIL |
| L3 | Class-specific surface | WARN |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (3 observation(s))
- Network
- declared (1 observation(s))
- Shell
- declared (8 observation(s))
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (17)
**Seed orientation context when the next moves are predictable.** Piggybacking a compact snapshot alongside the primary result — recent activity, tracked state, a few reference items — does two things
- **Mirror a bulk upstream instead of paginating it live.** When the server wraps a large or slow API whose corpus is queried far more than it changes, sync it once into a persistent local index and q
Exercise tools, resources, and prompts against a live HTTP server via MCP JSON-RPC over curl. Starts the server, surfaces the catalog, runs real and adversarial inputs, measures every call (bytes, tok
const tsc = await exec([join(ROOT_DIR, 'node_modules', '.bin', 'tsc'), '-p', project], 'tsc');
const alias = await exec(
exec(cmd: string[], options: { cwd: string }): Promise<ShellResult> {':(glob)**/.netrc',
| **Server credential** | The server's own upstream key is missing, or the upstream rejects it (401/403) | `ConfigurationError` — translated in the service, since the automatic status mapping yields `
Prereq: a GitHub PAT with `read:org` + `read:user` scopes stored in Keychain under the service name `mcp-publisher-github-pat`:
2. **No `git stash`, no `git reset --hard`, no `git restore .`, no `git clean -f`, no `git checkout -- .`.** These bypass safety and risk silent data loss. Read-only git (`status`, `diff`, `log`, `sho
multi-del
.mcpbignore
const seedDir = fileURLToPath(new URL('../../workflows-yaml/categories', import.meta.url));'../../workflows-yaml/categories/research-visualization/pubmed-research-with-cosmograph-visualization-workflow.yaml',
@cyanheads/mcp-ts-core, pino-pretty, semver, yaml, zod, @socketsecurity/bun-security-scanner, @types/semver, depcheck
- [ ] `.codex-plugin/mcp.json` updated — server name key is the unscoped repo name; every user-supplied variable (API key, contact email, instance URL) is listed in `env_vars` so Codex forwards it fro
- [ ] `.codex-plugin/mcp.json` updated — server name key is the unscoped repo name; every user-supplied variable (API key, contact email, instance URL) is listed in `env_vars` so Codex forwards it fro
Gates applied: critical_finding, instruction_override, no_behavioural_pass, undeclared_transfer.
616f6f04c9d4full audit observations/trust-audit/mcp-server/cyanheads__workflows-5.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-08 | 616f6f04c9d4 | BLOCK | F | 47 | first audit |
Questions
What is the Workflows MCP server?
Store, query, and create YAML workflow playbooks for LLM agents via MCP. STDIO or Streamable HTTP.
What tools does Workflows expose?
2 in total: 1 read-only, 0 that write, and 1 that can delete or overwrite (multi-del). Every one is listed on this page with its risk.
Is Workflows safe to connect to an agent?
No — not without reading the findings first. The audit graded it F (47/100) and found 10 critical or high issues in the source. Each one is listed on this page with the file and line it is on. Separately from the audit: 1 of its tools can destroy data, so scope the token you give it to what you actually need.
What credentials does Workflows need?
No credential environment variables were found in its source, so it appears to need none.
How does Workflows run?
It speaks stdio and streamable-http, so it runs as a local process your client starts. It is published on npm as @cyanheads/workflows-mcp-server at 0.4.1.
How current is this page?
The grade is for one exact copy of the source (616f6f04c9d4), read on 2026-10-08. The repository is watched and re-audited when it changes.