M
MCP Directory CURATED DIRECTORY
911 MCP servers indexed
中文
← Back to directory
C

Conversational API Debugger

Community
Debug REST API failures using OpenAPI specs and HTTP logs, with conversational root-cause analysis and cURL generation.
How to install ↓ Compare GitHub source repository ↗
Category
Dev Tools #433 of 438
Stars
★ 2.8k Very popular
Transport
stdio (local process)
Runtime
Node.js
Credentials
No credential needed
License
MIT
Last commit
20FMRS · D

Conversational API Debugger is a community MCP server for debugging REST API failures through OpenAPI specs and HTTP/HAR logs. The server manifest defines a stdio transport and an npm package (@claude-code-plugins-plus/conversational-api-debugger), and targets Claude Code's plugin marketplace. The README confirms its documented purpose: root-cause analysis with cURL generation. Specific tool names are not recorded in the provided source, and no unrelated capabilities from sibling servers were attributed to it. Verdict: a focused, reasonably scoped debugging server with modest but clear evidence.

Strongest · Maintenance 9/20 Weakest · Reliability 2/20

Reliability
2/20
Security and permissions
4/20
Maintenance
9/20
Documentation
2/20
Setup experience
3/20
Why each score
Reliability 2/20
Only the server manifest and repository-level README were reviewed; no source code, tests, or CI evidence for this specific server was supplied. The manifest describes an npm package over stdio and the concept is plausible, but there is no way to verify startup, the initialization handshake, or whether declared tools match real behavior. Under static calibration, unverifiable execution evidence caps the score. Deducted for missing implementation and test evidence.
Security and permissions 4/20
The manifest and README show no malware, leaked credentials, or red-line violations. However, there is no code-level evidence of credential handling, least privilege, data boundaries, or external network behavior. By description the server reads OpenAPI specs and HTTP logs, which can contain sensitive data, yet no confirmation flow or scoping disclosure is provided. Deducted for an entirely undocumented security posture.
Maintenance 9/20
The repository is not archived, has an MIT license, and the README indicates active releases and a validation pipeline; these are repository-level maintenance signals. However, there is no changelog, commit history, dependency update trail, or security response channel attributable to conversational-api-debugger specifically, so full marks were not given.
Documentation 2/20
No dedicated documentation for this server was provided. The repository README contains only a one-line catalog entry, and the manifest has just a name, title, and short description. Tool parameters, auth requirements, limits, costs, and troubleshooting are absent, making the server effectively undocumented for a new user.
Setup experience 3/20
The manifest declares an npm identifier and stdio transport, but the README only shows generic ccpi installation commands. There is no client configuration example, platform compatibility note, or verification step for this MCP server. Without real CI or test evidence showing a clean install path, the setup score is necessarily low.

Static review · not runListed 2026-08-07

Read the FMRS scoring method →

Fit and risk

What it can accessReads local filesUses the network

Best for

  • Claude Code users who want an assistant-oriented debugger for REST API failures.
  • Teams that have OpenAPI specs and HTTP/HAR logs and need structured root-cause analysis.
  • Developer workflows that prefer conversational iteration over paging through raw logs.

Not for

  • Non-REST debugging — the server is scoped to REST API failures via OpenAPI specs and HTTP logs; no support for other protocols is documented.
  • Replacing observability/APM platforms or automated test runners — only the documented debugging workflow is evidenced.
  • Users who need a known, enumerated list of tool names — the source material does not document the server's tool identifiers.

Required permissions

  • Read access to the OpenAPI spec files and HTTP/HAR logs it is asked to analyze.
  • A Node.js runtime able to run the npm package as a stdio child process of Claude Code.
  • Whatever filesystem and environment access Claude Code grants the plugin during the session.

Risks and side effects

  • Community-maintained rather than an official Anthropic or upstream-vendor server; verify conclusions before acting.
  • Analysis quality depends on the accuracy and completeness of the provided OpenAPI specs and logs.
  • Generated cURL commands should be reviewed before execution to avoid unintended side effects.

Setup

Before you start

Runtime：Node.js

  1. Install the ccpi CLI: pnpm add -g @intentsolutionsio/ccpi
  2. Install the server from the marketplace: ccpi install conversational-api-debugger

Or use Claude Code's built-in plugin commands:

  • /plugin marketplace add jeremylongshore/claude-code-plugins
  • /plugin install conversational-api-debugger@claude-code-plugins-plus

Check that it works

After installing @claude-code-plugins-plus/conversational-api-debugger via npm/stdio, confirm the Conversational API Debugger tools appear in your client's tool list.

Troubleshooting

  1. Confirm the marketplace is registered: `/plugin marketplace add jeremylongshore/claude-code-plugins`.
  2. If the plugin fails to load, reinstall it: `ccpi install conversational-api-debugger`.
  3. Make sure the OpenAPI and HAR/HTTP log files are accessible to Claude Code in the session.
  4. Check that Node.js and the npm package are available, and confirm the server is configured to use stdio transport.

Things to try

Once connected, you can ask your AI assistant things like:

  • Use this OpenAPI spec and HTTP log to figure out why my REST API request is failing
  • Analyze the root cause of this API failure and generate a debugging cURL command
  • Check these HTTP logs against the OpenAPI spec and flag requests that violate the contract

Use cases

Root-cause analysis of REST API failures using OpenAPI specs and HTTP/HAR logs.
Conversational debugging sessions inside Claude Code where failing endpoints are traced against their documented contracts.
Generating cURL commands to reproduce or verify failing API calls.

Supported clients

Claude Code

Listed from the project's documentation, not tested by this site.

Overview

Conversational API Debugger (v1.0.0) is a community MCP server published as the npm package @claude-code-plugins-plus/conversational-api-debugger. It is one of the MCP servers in the claude-code-plugins-plus-skills repository and is designed for Anthropic's Claude Code CLI. The server helps debug REST API failures by reasoning over OpenAPI specifications and HTTP logs (HAR), supporting root-cause analysis and the generation of cURL commands. It communicates over stdio. The provided source material does not enumerate specific tool names, so this profile describes only the server's documented capabilities and does not attribute any sibling server's functionality to it.

Similar servers

Context7 80 · B

Upstash's official server providing up-to-date third-party library docs for AI coding assistants

★ 62.9k · Tools 2 Compare with this →
Compare with other MCP servers

More servers from this repository

AI Experiment Logger MCP ServerAI Experiment LoggerDesign To CodeDomain Memory AgentLumera Agent MemoryProject Health AuditorWorkflow Orchestrator

Source revision ebea1067983c Data synced 2026-10-12 Read the FMRS scoring method