Moltline Studio
About
Fourteen hosted MCP servers over Streamable HTTP - code review, agent governance, business-day math, analytics, commerce math and SKILL.md linting - free tier needs no account or credentials.
Details
- Author
- garphengate
- Categories
- Developer Tools, Other, Automation
Jump to
Setup
Install Moltline Studio in your MCP client (Claude Desktop, Cursor, Windsurf, and others).
Repository: https://github.com/garphengate/moltline-mcp
Follow the installation instructions in the repository README, then restart your MCP client.
A thin, dependency-freestdio bridgetoMoltline Studio's fleet of19 hosted MCP servers.
Most modern MCP clients can connect to the fleetdirectly over Streamable HTTP— no install needed (seeDirect connectionbelow). This bridge exists for clients that only speak the stdio transport: it proxies newline-delimited JSON-RPC between your client and the hosted server, verbatim, with no telemetry and no dependencies beyond the Python 3.9+ standard library.
- 132 tools across 19 servers; 92 are free.
- Free tier:no registration, no account, no credentials— connect and call tools immediately.
- Premium tools are unlocked with a Moltline license, presentedonly as a tool argument(never in URLs or headers). Seeauth.md.
- Fleet is independently audited:MCPize Verified Aon direct endpoints.
Machine-readable discovery:api-catalog· per-server card athttps://mcp.moltlinestudio.com/<server>/.well-known/mcp/server-card.json·fleet health.
If your MCP client supports Streamable HTTP (Claude Desktop, Claude Code, Cursor, and most current clients do), point it straight at the hosted endpoint — nothing to install:
{ "mcpServers": { "moltline-timeops": { "type": "http", "url": "https://mcp.moltlinestudio.com/timeops" } } }
Swaptimeopsfor any slug in the table above.
The stdio bridge (for stdio-only clients)
Run directly (recommended)— the bridge is a single stdlib-only file, so a clone is all you need:
git clone https://github.com/GarphenGate/moltline-mcp.git python3 moltline-mcp/moltline_mcp.py timeops # any of the 19 slugs; default: catalog
Docker— seeDockerbelow if you prefer a container.
A PyPI package is planned; until then, use the methods above.
Point your MCP client at the script with an absolute path:
{ "mcpServers": { "moltline-timeops": { "command": "python3", "args": ["/absolute/path/to/moltline-mcp/moltline_mcp.py", "timeops"] } } }
Or run it through Docker (afterdocker build -t moltline-mcp .):
{ "mcpServers": { "moltline-timeops": { "command": "docker", "args": ["run", "-i", "--rm", "moltline-mcp", "timeops"] } } }
python3 moltline_mcp.py [server] [--timeout SECONDS] [--list] [--version]
- server— one of the 19 slugs (defaultcatalog); anything else fails fast with the valid list.
- --timeout— per-request timeout in seconds (default 300, or envMOLTLINE_TIMEOUT).
- --list— print the server slugs and exit.
- EnvMOLTLINE_BASE_URL— override the fleet base URL (for testing).
- EnvMOLTLINE_DEBUG=1— diagnostic logging on stderr (stdout stays protocol-clean).
The bridge also runs containerized (stdio in, network egress to the fleet required):
docker build -t moltline-mcp . docker run -i --rm moltline-mcp timeops # any of the 19 slugs; default: catalog
SeeClient configurationfor the matchingmcpServersentry.
One process per server connection. Each JSON-RPC message read from stdin is POSTed tohttps://mcp.moltlinestudio.com/<server>; JSON and SSE-framed responses are relayed back to stdout as newline-delimited JSON. The bridge tracks the server-assignedMcp-Session-Idand echoes the negotiatedMCP-Protocol-Version, per theStreamable HTTP transport spec. It never inspects, stores, or reports your traffic.
The bridge ships with an offline test suite - no network, no dependencies:
Twenty-two tests cover the parts that actually break in a transport bridge: newline-delimited framing, SSE event splitting (multiple events, multi-linedata:payloads, a trailing event with no blank line, comments and named events), session-id capture and reuse, protocol-version negotiation oninitializeonly, and error relay - a JSON-RPC error document is passed through verbatim, anything else becomes a well-formed-32603. CI runs them on Python 3.9, 3.12 and 3.13, plus a Docker build and container smoke test.
- Free tier— anonymous. No registration or credentials; all free tools work immediately.
- Premium— unlocked with a Moltline license purchased (human-in-the-loop) atmoltlinestudio.com. The license is passed as a tool argument where a premium tool asks for it — never as a bearer header, never in URLs. Details:auth.md.
- Website:https://moltlinestudio.com
- Agent access guide:https://moltlinestudio.com/auth.md
- API catalog:https://moltlinestudio.com/.well-known/api-catalog
- Agent protocol reference (x402, AP2, ACP, UCP, MPP, A2A):https://moltlinestudio.com/protocols.html
- Community:https://community.moltlinestudio.com
- Issues and security reports: seeSECURITY.md
This is a web browser that enables your coding agent, such as Claude Code, to visit websites on your behalf and assist you in identifying bugs or creating UI test cases.
Skene is a codebase analysis toolkit for product-led growth. It scan your codebase, detect growth opportunities, and generate actionable implementation plans.
An MCP service that equips your workspace with a complete set of AI-accessible development tools for reading, editing, executing, and managing code.
Code intelligence MCP server - PageRank, blast radius, co-change, hotspots, clone detection across 34 languages in a single Rust binary.
The MCP server for Bitrix24 provides AI assistants with structured access to the Bitrix24 API. It delivers up-to-date method descriptions, parameters, and valid values, allowing assistants to work with precise data instead of guesswork. This reduces code errors and accelerates Bitrix24 integration development.
Connect bugAgent to any MCP-compatible AI client. File, classify, and manage bugs, feature requests, and more directly from your AI coding assistant. No context switching, no copy-paste — just describe the issue and bugAgent handles the rest.
What Shopify did for ecommerce, Chipp does for AI agents. Build, deploy, and monetize AI agents for your business — no engineering team required.
CodeVF MCP lets AI hand off problems to real engineers instantly, so your workflows don’t stall when models hit their limits.
Boost security in your dev lifecycle via SAST, SCA, Secrets & IaC scanning with Cycode.
his repository contains a fully functional MCP (Model Context Protocol) server, providing solutions for Constraint Satisfaction Problems (CSP) and Linear Programming (LP). It is based on the gurddy package and supports solving a variety of classic problems.
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
