Slang Workflows MCP server

by shofer-dev·io.github.shofer-dev/slang-workflows·v0.1.2·1 stars

No reviews yet

Provable, declarative multi-agent workflows for Claude Code (typed .slang, non-LLM executor).

A91/100grade A

Write a review Install

What users say

No reviews yet

Be the first

Safety scan

A91/100

full report

Adoption

Growing

1 stars24 downloads/wk

Reviews

Write one

Nobody has reviewed Slang Workflows yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Slang Workflows tools (7, 1 write)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

get_slang_grammar
Return a concise slang grammar cheatsheet (constructs + a complete example) so you can GENERATE a workflow on the fly and run it inline via run_workflow(source). Validate generated source with validate_workflow(source) first; run_workflow also rejects parse/static-analysis errors.
get_topology
Return the current agent topology of a run as a Mermaid flowchart (nodes colored by status, plus live sending/waiting edges). Render it inline. Identify it by `workflow_id`.
get_trace
Return a run's execution trace as a Mermaid `sequenceDiagram` (round-by-round: who staked/routed to whom, commits, escalations, terminal event) plus the raw event log. The timeline counterpart to `get_topology`'s snapshot. Render the diagram inline. Identify it by `workflow_id`.
get_workflow_state
Return the serialized FlowState for a run started by `run_workflow`: per-agent status, opIndex, bindings, round, budget usage, and flow status. Identify it by `workflow_id`.
list_workflows
Discover .slang workflow files in the project (.claude/workflows/) and global (~/.claude/workflows/) directories. Returns each flow's name, title, params, and agent count.
run_workflowwrite action
Parse and run a .slang workflow to completion, dispatching each agent through the Claude Agent SDK and validating results against output contracts. Identify it by `name` or `path`; pass flow `params` as an object. Returns the final flow status and each agent's output. Rejects parse/static-analysis errors before running. Default runs synchronously (returns the final status + each agent's output). P
validate_workflow
Parse and statically analyze one workflow (deadlock detection, unknown refs, missing converge/budget, orphan outputs) without running it. Identify it by `name` or absolute `path`.

Public scan report

scanner v0.1.9 · 2026-09-26 · same rubric, same numbers if you re-run it

no findings

Code scan3 source files scanned25/25
–Live reliabilityno gateway calls yet and no remote to proben/a
–Tool poisoningtools not inspected (local package is not executed); not countedn/a
Auth qualitylocal package, no credentials required12/15
Maintenancelast push 28 days ago15/15
Maintainer identityregistry namespace matches repository owner7/10

Overall 91/100. Components that don't apply are left out of the denominator. Any critical finding is an F.Rubric Appeal a finding JSON

How Slang Workflows compares

Against every graded AI and agents MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score: 91/100; higher than 88% of 4,460 AI and agents servers
Tools: 7; the typical AI and agents server has 6
Tools that change things: 14%; typical: 0%. Fewer write tools means less an agent can break
GitHub stars: 1; more than 50% of 2,711 AI and agents servers
Downloads a week: 24; more than 10% of 1,538 AI and agents servers with a package

What its tools let an agent do: 6 read · 1 run or deploy

Install Slang Workflows in Claude Code, Cursor or VS Code

Runs npx -y slang-workflows on your machine. Read the scan report first; the gateway never runs local packages.

claude mcp add slang-workflows -- npx -y slang-workflows

Add to Cursor

What the publisher says

From the Slang Workflows repository's README, as published. We do not edit it. Read it on GitHub

███████╗██╗      █████╗ ███╗   ██╗ ██████╗
██╔════╝██║     ██╔══██╗████╗  ██║██╔════╝
███████╗██║     ███████║██╔██╗ ██║██║  ███╗
╚════██║██║     ██╔══██║██║╚██╗██║██║   ██║
███████║███████╗██║  ██║██║ ╚████║╚██████╔╝
╚══════╝╚══════╝╚═╝  ╚═╝╚═╝  ╚═══╝ ╚═════╝
     provable, declarative multi-agent workflows for Claude Code
     a non-LLM executor runs your typed .slang files

slang-workflows

Run provable, .slang-driven multi-agent workflows inside Claude Code.

A non-LLM state machine (the slang executor) runs inside an MCP server and coordinates agents; each agent is a Claude Agent SDK session. You declare the collaboration in a typed .slang file and the executor enforces it — typed output contracts, static analysis, tool-scoping, and provable termination — instead of leaving coordination to the model. The top-level Claude Code session only triggers and observes; it never makes a coordination decision.

Claude Code's native dynamic workflows also codify orchestration (Claude writes a JS script); slang's difference is that the structure is enforced and statically analyzable, and runs render as Mermaid topology + trace diagrams. See the benchmark for the A/B/C head-to-head.

Origin. The .slang Workflow engine was born in Shofer — the

AI-agent VS Code extension — where the deterministic, non-LLM executor was first built. This

plugin brings it to Claude Code.

Design and rationale: DESIGN.md. Language reference: slang_specs.md. Privacy: PRIVACY.md.

How it works

flowchart TB
    You(["You"])
    CC["Claude Code<br/>top-level session"]

    subgraph server["slang-workflows · MCP server"]
        direction TB
        SL["your .slang workflow<br/>agents · stakes · contracts · converge"]
        EX["slang executor<br/>deterministic · non-LLM state machine"]
        MB[("FlowState + mailbox")]
        SL -->|"parsed once"| EX
        EX <--> MB
    end

    subgraph Agents["Agent SDK sessions — the agents your .slang declares"]
        direction LR
        A1["Agent A"]
        A2["Agent B"]
        A3["Agent …"]
    end

    You <-->|"ask · approve escalations"| CC
    CC -->|"run_workflow"| EX
    EX -->|"topology + trace diagrams"| CC
    EX ==>|"dispatch stake — one session per agent, resumed"| Agents
    Agents ==>|"typed result → output-contract check + retry"| EX
    EX -.->|"escalate @Human"| CC

    classDef brain fill:#eaeaff,stroke:#5b5bd6,stroke-width:2px;
    class EX brain;

The top-level Claude Code session only triggers and observes — it never makes a coordination decision. The non-LLM executor reads your .slang file, dispatches each stake to an Agent SDK session (one long-lived session per agent, resumed across rounds), checks every result against its output contract (retrying on failure), routes it through the mailbox, and repeats each round until the workflow's converge condition or round budget is met. Runs render as Mermaid topology and trace diagrams; escalate @Human surfaces back to you in the normal chat.

Use cases

Concrete workflows (each is a .slang file you run with run_workflow):

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Slang Workflows: common questions

Is Slang Workflows MCP server safe?: Yes, by our scan: it is graded A (91/100). Read the Slang Workflows safety report
How do I install Slang Workflows?: It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Slang Workflows need an API key?: Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is Slang Workflows maintained?: The last commit was 67 days ago (2026-08-29). The latest release is v0.1.2.
What can I use instead of Slang Workflows?: Servers from other publishers that do the same job: PaperBanana MCP server, three.ws Brain MCP server and Claude Prompts MCP server.
How does Slang Workflows compare with other AI and agents MCP servers?: safety score 91/100 (higher than 88% of 4,460 AI and agents servers); tools 7 (the typical AI and agents server has 6); tools that change things 14% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.

Alternatives to Slang Workflows

Same job from other publishers: the closest match first, then the best rated.

PaperBanana
Generate academic diagrams and statistical plots from text using multi-agent AI.
not reviewed
Established
A
three.ws Brain
List LLM providers and run chat completions through the three.ws multi-provider router.
not reviewed
Established
B
Claude Prompts
Reusable prompt templates, multi-step workflow chains, and quality gates for any MCP client.
not reviewed
Established
A