Fixzi — MCP & API Schema Drift Monitor

io.github.rohitcodilyaPublished by GitHub account rohitcodilyav1.0.2Updated Oct 24, 2026

Monitor MCP servers, API contracts and AI outputs for schema drift. Alerts on breaking changes.

VerifiedStreamable HTTPWeb executableDeveloper ToolsSecurity & Monitoring

Overview

AI-generated overview

Fixzi's remote MCP server lets an assistant list, inspect and run schema-drift monitors for MCP servers, API contracts and AI output validators.

What you can do
  • List monitors and read one monitor's status, last check result and consecutive failures
  • Review a monitor's change log with severity and before/after details, and view the current tool list of a monitored MCP server
  • Trigger a check immediately and create a new MCP server monitor from a URL
  • List AI output validators, read validator details, run a validation check and review recent check history
When to use it
Useful when you already use Fixzi to watch MCP servers, API contracts or AI output schemas and want to query or operate those monitors from Claude Code, Cursor or another MCP client, for example to check whether a server changed this week or to set up a monitor for a newly deployed endpoint.
Requirements
Remote streamable HTTP endpoint at fixzi.ai; OAuth is declared, and the README shows connecting with an Authorization Bearer API token created in Fixzi settings, with abilities granted per tool. MCP server access requires the Pro+ plan; the web app has a free tier.
Before you install
The API token is a credential passed in the Authorization header and should be scoped to only the abilities needed. Some tools write: creating monitors and running checks require monitors:write, and running validations requires validators:check. MCP access is a paid Pro+ feature.

Installation

In SourceWeft

  1. Open Fixzi — MCP & API Schema Drift Monitor in the dashboard and add it to a workspace.
  2. Connect the required credentials. They are stored privately and never shown on public pages.
  3. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/io.github.rohitcodilya%2Ffixzi-mcp/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config. The client completes OAuth sign-in on first connect.

{
  "mcpServers": {
    "fixzi-api-schema-drift-monitor": {
      "type": "http",
      "url": "https://fixzi.ai/api/mcp"
    }
  }
}

README

Fixzi MCP Server

Monitor MCP servers, API contracts, and AI output schemas — from inside Claude Code, Cursor, or any MCP client.

Your MCP servers, APIs, and AI outputs can break while still returning 200. Fixzi watches the contracts your integrations depend on, classifies every change (breaking / warning / info), and alerts you before your users hit it. This MCP server lets your AI tools query and operate those monitors directly.

Connect

Claude Code

bash
claude mcp add --transport http fixzi https://fixzi.ai/api/mcp \  --header "Authorization: Bearer YOUR_FIXZI_API_TOKEN"

Or add to your project's .mcp.json:

json
{  "mcpServers": {    "fixzi": {      "type": "http",      "url": "https://fixzi.ai/api/mcp",      "headers": {        "Authorization": "Bearer YOUR_FIXZI_API_TOKEN"      }    }  }}

Claude Desktop

Add to claude_desktop_config.json:

json
{  "mcpServers": {    "fixzi": {      "type": "streamable-http",      "url": "https://fixzi.ai/api/mcp",      "headers": {        "Authorization": "Bearer YOUR_FIXZI_API_TOKEN"      }    }  }}

Get your API token at https://fixzi.ai/settings/api-tokens. When creating the token, grant the abilities for the tools you want to use (see below).

Tools

Monitoring (MCP servers, API contracts, AI validators)

ToolWhat it doesAbility required
fixzi_list_monitorsList all your monitors (MCP / API contract / AI validator) with health status—
fixzi_get_monitor_statusCurrent status, last check result, consecutive failures for one monitor—
fixzi_get_recent_changesChange log for a monitor: severity, what changed, before/after (filter by date/severity)—
fixzi_get_current_snapshotCurrent tool list of a monitored MCP server (names, descriptions, schemas)—
fixzi_run_check_nowTrigger a check immediately (async — poll status after)monitors:write
fixzi_create_mcp_monitorCreate a new MCP server monitor from a URLmonitors:write

AI output validation

ToolWhat it doesAbility required
fixzi_list_validatorsList your AI output validatorsvalidators:read
fixzi_get_validatorDetails of a specific validatorvalidators:read
fixzi_run_checkRun a validation check right nowvalidators:check
fixzi_list_checksRecent check historyvalidators:read

Example prompts

Once connected, ask your agent things like:

  • "Check if my MCP server changed this week" — chains fixzi_list_monitors → fixzi_get_recent_changes
  • "Is my payments API contract still healthy?"
  • "Set up a monitor for the MCP server I just deployed at https://example.com/mcp"
  • "Run my product-description validator and tell me if the schema still passes"

Requirements

  • MCP server access requires the Pro+ plan — see https://fixzi.ai/pricing
  • Fixzi's web app includes a free tier (1 monitor of each type, daily checks, email alerts) and free tools, including a no-signup MCP Server Checker to test any MCP server instantly.

Learn more

Source: README.md at commit 5940825

Tools

0
This server asks for a credential such as an API key, so SourceWeft could not read its tools without one and has not indexed them.

Version history

1
  1. v1.0.2LatestSep 16, 2026

Score

75% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts

    Declare a license in the repository or the registry entry.