mcp-contract-testing
Skill0 starsChanged 15 days agoMITView on GitHub
Test MCP server boundaries and cross-language protocol behavior in the Cassandra MCP repository, including rejected calls and secret-safe output.
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 0 are distinctive, and 1 is 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.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 12
Use the documented build and test commands for the changed implementations, then node scripts/check_transports.mjs for the real executable …
≈ “Common” is an estimate: at least 1 in 5 of the 308,232 skill 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.
Files
Test the MCP contract
Author: Sandeep Belgavi
Use the documented build and test commands for the changed implementations, then node scripts/check_transports.mjs for the real executable handshake checks. Test database policy against controlled fixtures; do not run mutation probes against a user's live cluster without authorization.
Evidence should cover authorization before database access, exact composite keys, parameter binding, selected-column validation, row limits, concurrency, oversized output, rate limits and redacted failures. Test malformed arguments through an MCP client as well as the service method: SDK validation can differ by language.
Separate fixture tests, real transport tests, live database checks and hosted CI results in your report. If a change only affects one language, run its unit tests and the shared protocol contract; broader testing is warranted when shared semantics change. A successful tool list does not prove queries work. Keep stdout exclusively for JSON-RPC while running servers.
In this repository3 other files it gives its agents.
- AGENTS.mdAGENTS.md
- cassandra-readonly-setupSkill
- mcp-server-selectionSkill
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
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.

