
Latchpoint
io.github.robyrorov0.1.1Updated Oct 9, 2026
Offline, read-only auditing of MCP client configuration files with redacted findings
Overview
Lets an assistant audit MCP client configuration files offline and read-only, returning redacted findings as text, JSON, or SARIF.
- What it does
- Latchpoint scans MCP client configuration files without running the servers they describe. It exposes two tools, list_rules and scan, and checks rules such as plain HTTP for non-loopback endpoints, shell wrappers, unpinned npx or uvx packages, literal credentials, broad filesystem scopes, wildcard hosts, and invalid transport settings. Findings carry a stable rule ID, severity, location, remediation, redacted evidence, and a confidence note. Results can be text, JSON, or SARIF.
- When to use it
- Use it when you want to review MCP client configuration files for risky patterns before or after installing servers, or to add a configuration check to a build. It suits defensive review of local configs rather than runtime testing of a server.
- Requirements
- Local Python 3.11 or newer; installable from PyPI as mcp-latchpoint or run with uvx. The stdio server needs an allowed root directory passed at startup with --root, and relative scan paths are resolved below it. No accounts, API keys, or network access are declared.
Installation
In SourceWeft
- Open Latchpoint in the dashboard and add it to a workspace.
- Enable the server for the chats that should use its tools.
Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.
Other MCP clients
Follow the launch instructions in the repository.
README
mcp-latchpoint
mcp-latchpoint audits MCP client configuration files without running the configured servers. It works offline, reads only local files you select, and produces text, JSON, or SARIF results.
This is an early defensive tool. Review findings in context before changing a working configuration.
What it checks
The v0.1 rules cover:
- plain HTTP for non-loopback remote endpoints
- shell wrappers and inline shell control syntax
- identifiable
npxanduvxpackages without exact versions - literal credentials in environment values, headers, arguments, or URLs
- filesystem roots and home roots passed as recognizable access scopes
- wildcard hosts and recognizable wildcard scopes
- conflicting, missing, invalid, or unsupported transport settings
Every finding has a stable rule ID, severity, location, remediation, redacted evidence, and a confidence note when interpretation depends on the launched server.
Install
Python 3.11 or newer is required.
To install from a local checkout:
For development:
The MCP server uses the official Python SDK v2 and the dependency is constrained to mcp>=2.3,<3.
CLI
Scan one or more explicit files:
Restrict every explicit path to an approved directory:
Directories are searched only for recognized MCP config filenames, up to 256 files. A file is limited to 1 MiB by default. Change these bounds with --max-files and --max-bytes.
Exit codes are 0 for a completed scan below the chosen threshold, 1 when a finding meets --fail-on, and 2 for input, containment, or parse errors. The default --fail-on none reports findings without failing a build.
List and explain rules:
Recognized layouts
Explicit files may use these structures:
Files ending in .jsonc are also parsed as JSONC. Other .json files remain strict JSON so malformed input is not silently accepted.
--discover checks only the following paths when they exist. It does not search the rest of the home directory.
- All systems:
~/.claude.json,~/.cursor/mcp.json,~/.codex/config.toml,$COPILOT_HOME/mcp-config.jsonwith~/.copilot/mcp-config.jsonas the fallback - Current project:
.mcp.json,.codex/config.toml,.cursor/mcp.json,.vscode/mcp.json - Windows:
%APPDATA%\Claude\claude_desktop_config.json,%APPDATA%\Code\User\mcp.json - macOS:
~/Library/Application Support/Claude/claude_desktop_config.json,~/Library/Application Support/Code/User/mcp.json - Linux:
$XDG_CONFIG_HOME/Code/User/mcp.json, falling back to~/.config/Code/User/mcp.json
Read-only MCP server
The stdio server exposes two tools: list_rules and scan. It requires an allowed root at startup. Relative scan paths are resolved below that root; absolute paths, .. traversal, and symlinks cannot escape it.
Example client entry:
The server returns findings and scan metadata, never raw configuration content. Stdio is the only server transport exposed by the entry point, and stdout is reserved for MCP protocol messages.
The serve command is also the entry point advertised in the MCP Registry. Set --root to a directory you explicitly trust before connecting a client.
Glama build
The Glama listing builds a container from the repository. In its Dockerfile configuration, use Python 3.13, these build steps and command arguments:
The root is an existing directory with synthetic sample configurations. It lets Glama start and inspect the tools without giving the server access to a user's files. The command uses the executable inside the virtual environment created by uv sync. For this demo, the environment-variable schema can be {"type":"object","properties":{}} and placeholder parameters can be {}.
To scan your own configurations, run the server locally with --root pointing to a directory you explicitly trust. Glama's demo root is only for the sample files in examples/.
Safety and limitations
The scanner never executes commands, installs packages, resolves referenced environment variables, or connects to endpoints. It does not follow configuration includes or inspect an MCP server's code or runtime behavior. Argument-based rules are intentionally limited to recognizable patterns, so custom flags can be missed. A clean report is not proof that a server is safe.
Secret detection is designed to emit field names and <redacted> markers rather than values. If you find a leak or a path-containment problem, follow SECURITY.md and do not attach a real configuration to a public issue.
License
MIT. See LICENSE.
Source: README.md at commit b5f65df
Tools
0Version history
1- v0.1.1LatestOct 9, 2026

