@TinyMurky
Basic information
mcp server for llm to test api
No standard config provided
This server doesn't expose a parseable MCP config block in its README. See the repository for install instructions.
RepositoryTool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
mcp-api-tester Tools & Interfaces is a set of MCP tools that enable a Large Language Model (LLM) to perform automated API testing. It provides interfaces for reading API documentation, selecting endpoints, and sending real HTTP requests via the net/http package, targeting developers who want to quickly identify potential issues in their APIs.
The tools are invoked via MCP tool calls. For example, to use the ReadOpenAPIDocument tool, send a JSON-RPC request with method: "tools/call" and parameters including the tool name and arguments such as an absolute path to the OpenAPI file. Similarly, ListAllAPIFromDocument can be called without arguments. The README recommends first integrating the three minimal viable tools (listAllAPIFromDocument, getSingleAPIDetail, callNetHTTP), then connecting the LLM to use them, and optionally adding validation, logging, environment management, and fuzz testing tools.
ReadOpenAPIDocument toolThe three essential tools are `listAllAPIFromDocument` (lists available APIs), `getSingleAPIDetail` (retrieves detailed documentation for an endpoint), and `callNetHTTP` (sends real HTTP requests and returns responses).
An optional advanced tool `getAuthToken(username, password) -> token` is provided for APIs that require a token or cookie. The LLM can call this first to obtain credentials before making test calls.
No. The README explicitly notes that while the LLM can quickly produce boundary and abnormal test cases, traditional unit tests remain essential for thorough coverage and cannot be replaced.
All API tests should be run in a safe environment (development or sandbox) to avoid compromising sensitive data. The README also warns that the LLM may produce invalid or incorrect parameters, so additional validation or error handling may be needed.
Advanced tools include `storeTestResult` to log execution details and outcomes, and `getTestHistory` to query past results for a given endpoint, helping to identify regressions over time.
SSH MCP server for AI agents: remote commands, file transfer, log search and server audits through OpenSSH.
Agent Trust — open profile + reference implementation for proving what an autonomous AI agent is authorized to do: identity, delegation with attenuation, proof-of-possession, attestations, tamper-evident provenance. Buil
Local-first credential broker for MCP. AI coding agents (Claude Code, Cursor, Codex…) call APIs, SSH and databases through scoped presets; secrets stay in your OS keychain and never enter the agent's context.
OrangePro local-first CLI + MCP server for behavior mapping, grounded test generation, and dynamic proof.
Collide is the multiplayer layer for AI coding agents, and it pays for itself. Expert orchestration across every agent on your repo saves teams tens to hundreds of dollars a day in token burn. Run Claude Code, Codex, Cu
Comments