MCP proxy server and tool enforcement gateway for Dmint
Wellknown found it in public sources; nobody has proven control of it yet. Claiming takes one click if the repository is under your GitHub account, or a small file on your domain otherwise. Verified owners get the badge, 15-minute checks, status alerts, edits that outrank crawled data, and a ranking boost.
Agents can do it too: POST https://wellknown.network/api/v1/claims with {"agent":"dmint-mcp","method":"well_known_file"} — machine-readable steps at claim.json, guide at /docs/claim.
Everything here was measured by our prober or read from a registry. Nothing is self-reported.
Attributed to the source that supplied each field. Treated as claims, not facts.
# dmint-mcp [](https://github.com/dmint-app/dmint-mcp/actions/workflows/ci.yml) [](https://pypi.org/project/dmint-mcp/) [](https://pypi.org/project/dmint-mcp/) [](LICENSE) Security enforcement gateway for Model Context Protocol (MCP) servers. `dmint-mcp` connects AI agents (Cursor, Claude Code, Antigravity) to downstream MCP servers under deterministic policy control. It intercepts `tools/call` invocations, blocks unapproved actions before execution, and protects remote endpoints against SSRF and metadata exfiltration. --- ## Installation ```bash pip install dmint-mcp ``` --- ## Quickstart ### 1. Configure Protection (`mcp_protection.json`) ```json { "policy_file": "policy.json", "approval_db": "./approvals.sqlite3", "approval_ttl": 300, "integrations": [ { "integration_id": "postgres", "transport": "stdio", "connection": { "command": "npx", "args": ["-y", "@modelcontextprotocol/server-postgres", "postgresql://localhost/mydb"] }, "tool_bindings": { "query": { "tool_name": "query", "capability": "postgres.query", "discovery": "exposed" } } } ] } ``` ### 2. Run the Gateway ```bash dmint-mcp run --config mcp_protection.json ``` Or configure your AI client (e.g. `.cursor/mcp.json`): ```json { "mcpServers": { "protected-db": { "command": "python", "args": ["-m", "dmint_mcp", "run", "--config", "/path/to/mcp_protection.json"] } } } ``` --- ## Key Capabilities - **Pre-Execution Gate**: Unapproved (`APPROVAL_REQUIRED`) and forbidden (`DENY`) tool calls are halted before reaching downstream server processes. - **SSRF Defenses**: Validates remote HTTP end…
Mapped onto the structured taxonomy from declared text and observed tool names. Confidence shown for derived entries.
Every source is kept verbatim. Field changes are logged as events.