agentleFS
bvenkatabvenkata/legacy2mcp/.cursor/rules/legacy2mcp.mdc

legacy2mcp / rules

Cursor rule7 starsChanged 10 days agoApache-2.0View on GitHub

legacy2mcp -- legacy SOAP/DB/REST to MCP server

We split this legacy2mcp.mdc into the rules it gives an agent

3 rules. About 0 are common, 0 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Start the MCP server (an MCP client normally launches this itself -- running it by hand just blocks waiting for a client over stdio): …

    line 26
  2. Very specific:

    After init, review config.yaml's # TODO comments and the plain-English config.html report before trusting the generated config -- it's a …

    line 30
  3. Very specific:

    Write-like operations stay hidden unless allow_write_operations: true is set explicitly, and every tool call is audit-logged to …

    line 33

≈ “Common” is an estimate: at least 1 in 5 of the 6,350 Cursor rule files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
legacy2mcp.mdc
---
description: legacy2mcp -- legacy SOAP/DB/REST to MCP server
globs: []
alwaysApply: false
---

legacy2mcp turns an existing SOAP/WSDL service, a database, a REST API, or a
plain website with no API docs into a safe, typed, audit-logged MCP server
-- read-only by default, every call audit-logged, no hand-written adapter
code or hand-maintained schemas.

Common commands:

- Point at a live WSDL (no API key needed; zeep introspects it live):
    legacy2mcp init --wsdl-url "https://service.example.com/Legacy?wsdl" --out config.yaml
- Point at a live REST API (tries OpenAPI/Swagger discovery, no API key needed):
    legacy2mcp init --rest-url "https://api.example.com" --out config.yaml
- Point at a website with no API docs at all (crawls it for forms/content;
  every operation lands confidence=low/needs_review=true -- review before trusting):
    legacy2mcp init --webpage-url "https://your-legacy-app.example.com/some-page" --out config.yaml
- Scan a GitHub repo or local codebase for a SOAP client / ORM model / routes:
    legacy2mcp init --github-url https://github.com/you/your-api --scan-only --out config.yaml
    legacy2mcp init --local-path ./path/to/repo --scan-only --out config.yaml
- See the real discovered tools before trusting anything (no server started):
    legacy2mcp inspect --config config.yaml
- Start the MCP server (an MCP client normally launches this itself --
  running it by hand just blocks waiting for a client over stdio):
    legacy2mcp run --config config.yaml

After `init`, review config.yaml's `# TODO` comments and the plain-English
config.html report before trusting the generated config -- it's a static/
introspected best effort, not yet verified against the live backend.
Write-like operations stay hidden unless `allow_write_operations: true` is
set explicitly, and every tool call is audit-logged to
./legacy2mcp-audit.log. Database access is an explicit table/column
allowlist generated from the live schema -- never arbitrary SQL.

To wire the generated server into an MCP client, add to its config (use an
absolute path to config.yaml):
    {"mcpServers": {"<name>": {"command": "legacy2mcp", "args": ["run", "--config", "/absolute/path/to/config.yaml"]}}}

Full docs: https://github.com/bvenkata/legacy2mcp

Download now (ZIP)

  • Where files are headingNew Cursor rule files have more rules about planning and tracking tasks, and fewer about code style.

    Of the Cursor rule files we read, the 3,978 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.

  • In this repository3 other files it gives its agents.

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.