api-testing-mcp CLAUDE.md

Project instructions for an MCP server that lets AI assistants test APIs locally, storing data in JSON files instead of a cloud service. MCP is a standard way for AI assistants to call external tools.

In plain words
What is it for?
Use it when developing, testing, or changing the API-testing tools, response filtering, cached responses, validation, or integration tests.
Why use it?
It explains the server's structure and how to limit returned data, which helps keep large API responses from filling the assistant's context.

Instructions file

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/cocaxcode/api-testing-mcp/claude-md
Clone the repo
git clone --depth 1 https://github.com/cocaxcode/api-testing-mcp
Per session 959 This file is loaded in full into every session.
When invoked 959 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00959 $0.00959
Opus 5 $0.00479 $0.00479
Sonnet 5 $0.00192 $0.00192
Haiku 4.5 $0.00096 $0.00096

Measured 2d ago against content hash 5f62c7ae06d8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

api-testing-mcp CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 82 lines

How it starts

The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — @cocaxcode/api-testing-mcp

Project Overview

MCP server for API testing. Zero cloud dependencies, local JSON storage. 42 tools, 171 tests.

Token-optimized responses (v0.13+)

request accepts three optional parameters that cut context tokens by 70-97%:

  • verbosity: 'minimal' | 'normal' | 'full' (default 'normal')
  • only_fields: string[] with dot-paths (data.id, items[*].name)
  • max_body_bytes: number (default 2048) for 'normal'

Every compressed response includes a call_id. Use inspect_last_response({ call_id }) to recover the full unfiltered response when needed. Responses are cached in a 20-slot ring buffer + .api-testing/last-responses/ with 1h TTL.

Header filter lists live in lib/compress.ts (FILTERED_HEADERS, FILTERED_HEADER_PATTERNS).

Stack

  • TypeScript 5.x (strict mode, ESM)
  • @modelcontextprotocol/sdk 1.27.x (unified package)
  • Zod 3.25+ for schema validation
  • Vitest for testing (InMemoryTransport for integration tests)
  • tsup for building (ESM output with shebang)

Architecture

src/
├── index.ts          # Entry point (shebang + StdioServerTransport)
├── server.ts         # createServer() factory
├── tools/            # MCP tool registration (one file per group)
│   ├── request.ts    # HTTP request tool (1)
│   ├── collection.ts # Collection CRUD tools (4)
│   ├── environment.ts # Environment tools (10)
│   ├── api-spec.ts   # OpenAPI import/browse tools (4)
│   ├── assert.ts     # Assertion testing tool (1)
│   ├── flow.ts       # Request chaining tool (1)
│   ├── mock.ts       # Mock data generation tool (1)
│   ├── load-test.ts  # Load testing tool (1)
│   └── utilities.ts  # export_curl, diff_responses, bulk_test, export/import_collection, export/import_environment, export/import_postman_collection, export/import_postman_environment (11)
├── lib/              # Business logic (no MCP dependency)
│   ├── types.ts      # Shared TypeScript interfaces
│   ├── schemas.ts    # Shared Zod schemas (AuthSchema, HttpMethodSchema)
│   ├── url.ts        # resolveUrl() — BASE_URL auto-prepend
│   ├── path.ts       # getByPath() — dot notation accessor
│   ├── http-client.ts # fetch wrapper with timing
│   ├── storage.ts    # JSON file storage in .api-testing/
│   ├── interpolation.ts # {{variable}} resolver
│   └── openapi-parser.ts # OpenAPI spec parser with $ref + allOf/oneOf/anyOf
└── __tests__/
    ├── helpers.ts    # createTestClient() with InMemoryTransport
    └── *.test.ts     # 10 test files, 110 tests

Read the full file on GitHub · 82 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 82 lines · 959 tokens per session scan A 5f62c7ae06d8

Subscribe to this mod's changes

api-testing-mcp CLAUDE.md is an instructions file published in the GitHub repository cocaxcode/api-testing-mcp (6 stars, last pushed 4mo ago), licensed MIT. It adds 959 tokens to every session, about $0.0048 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.