Fixme Agent runs on your own machine — the client starts it, so there is no endpoint to ping. 32 installs a week from npm.
Real-time AI code quality — 30 validators, 17 languages, 813+ checks
The linked repository no longer exists on GitHub — it was deleted or made private.
Quiet is not dead — but it is worth knowing when it wakes up, or when someone else takes it over. We watch the repository and tell you either way.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add fixme-agent -- npx -y fixme-mcp
{
"mcpServers": {
"fixme-agent": {
"args": [
"-y",
"fixme-mcp"
],
"command": "npx"
}
}
}
[mcp_servers.fixme-agent]
command = "npx"
args = ["-y", "fixme-mcp"]
{
"mcpServers": {
"fixme-agent": {
"args": [
"-y",
"fixme-mcp"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"fixme-agent": {
"args": [
"-y",
"fixme-mcp"
],
"command": "npx"
}
}
}
This one needs environment variables set before it will start:
FIXME_TOKEN (Your FixMe license token (get one at https://fixme-now.com)).
The author declared them in the registry entry; get the values from the project itself.
OpenIBAN MCP — validate an IBAN's checksum + bank code and resolve the
Structural code-quality tools for AI coding agents.
16 checks on a system-security-plan JSON, in your editor, before a validator returns the package
Automated codebase refactoring and type safety validator.
Quality gates for AI agents. Lint, test, build checks with memory persistence.
Code graph MCP: 81 languages, 88 frameworks, 72.7% fewer PR-review tokens, comprehension at parity
Validates AI infra code on real VMs. Self-corrects until it works. No containers, no sandboxes.
Semantic code graph: 42 tools, 38 languages. Callers, impact, AI context, memory, PR review.
Answers built from our own checks of this server.