Calllint MCP Server
Your agent can run tools faster than you can review them. CallLint is a pre-flight risk linter for MCP and agent-tool configs. It checks the blast radius before the tool runs: what each tool can read, write, execute, connect to, send, or mutate - then returns an evidence-backed verdict (SAFE / REVIEW / BLOCK / UNKNOWN) before your agent ever loads the server.
People connecting security tools to Claude, Cursor, VS Code, or another MCP client. The project is written in TypeScript.
VERIFIED ACTIVE
LAST COMMIT 2026-08-25 · ★ 2 · #71 OF 182 MAINTAINED SECURITY · VERIFIED 2026-08-25
Apache-2.0 · TypeScript servers · how we verify → /methodology
01 · Install Calllint
Claude Code
claude mcp add calllint-calllint -- npx -y calllint-mcp Claude Desktop / Cursor / VS Code - add to config
{
"mcpServers": {
"calllint-calllint": {
"command": "npx",
"args": [
"-y",
"calllint-mcp"
]
}
}
} Same JSON for Cursor. For VS Code, rename the top-level key from `mcpServers` to `servers`.
Using another client? Same JSON, different key
Claude Desktop · mcpServers
Cursor · mcpServers
VS Code · servers
Windsurf · mcpServers
Zed · context_servers
Cline · mcpServers
Roo Code · mcpServers
Continue · mcpServers
LibreChat · mcpServers
Gemini CLI · mcpServers
Codex CLI · mcp_servers
Full setup guides: every client.
02 · Evidence
Security posture
What to check before giving this server access to your agent - from the registry, GitHub, and our own probes. We don't score safety; we show what's verifiable.
runs as local process (stdio) - runs on your machine with your user's permissions
license Apache-2.0 - declared in the repository
npm package calllint-mcp - unscoped; check the name against the project README before installing
registry namespace io.github.calllint is GitHub-verified and matches the repo owner
03 · What Calllint can do
Prose above is summarized from the project's README and registry record - no invented capabilities.
Limitations (from the README)
CallLint sees configuration, not behavior. It can miss risks a server only reveals at runtime, and can flag surface that turns out benign. It depends on the tool metadata you provide being accurate, and a server can change after you approve it (use baseline / verify to catch that). It is heuristic: expect both false positives and false negatives, and treat REVIEW/BLOCK as the start of a review, not a complete threat
Latest releases
v1.8.0 · 2026-08-18
[1.8.0] - 2026-08-18 - Phase 2.4-B gate closure + Trust Index D1-D3 + R-9 backup · Added · Workstream T PR T0 + Workstream R §8.6 - the trajectory-readiness audit lands where it can · actually be delivered, and the…
v1.7.3 · 2026-07-22
A distribution-productionization patch. It cuts what accumulated on main after 1.7.2: · CallLint ingests its own MCP server and runs the first real claim reconcile · (dogfood), the embedded-distribution /…
v1.7.2 · 2026-07-21
Distribution breadth, telemetry wiring & CI/scale-out hygiene. A hardening + plumbing · patch. No change to scan behaviour, the ScanReport schema, or the verdict vocabulary - · the deterministic engine is unchanged…
04 · Who maintains Calllint
calllint is maintained by calllint. It's the only MCP server we track from this author; the repo dates to Jun 2026.
05 · Facts
- repository
- github.com/calllint/calllint
- website
- https://calllint.com/
- category
- security - ranked #71 of 182 actively-maintained security servers as of 2026-08-25.
- release cadence
- 10+ releases in the last 90 days (latest 2026-08-18)
- registry
- io.github.calllint/calllint (active, first published 2026-06-30 · 2 versions)
- packages
- npm:calllint-mcp
06 · Calllint FAQ
What is Calllint?
Your agent can run tools faster than you can review them. CallLint is a pre-flight risk linter for MCP and agent-tool configs. It checks the blast radius before the tool runs: what each tool can read, write, execute, connect to, send, or mutate - then returns an evidence-backed verdict (SAFE / REVIEW / BLOCK / UNKNOWN) before your agent ever loads the server.
Is Calllint still maintained?
Yes - as of 2026-08-25, its last commit was 2026-08-25 and it shipped 10+ releases in the last 90 days. We re-verify nightly.
How do I install Calllint?
Run `npx -y calllint-mcp`. You can also paste the ready-made client config above.
Does Calllint run locally?
Yes - it's a stdio server: it runs on your machine (via npx) with your user's permissions. Your data stays local unless the server itself calls external APIs.
07 · Alternatives to Calllint
Alternatives to Calllint
Maintained security servers if Calllint isn't the fit.
- SafeDep Vet MCP Protect your AI agents and IDEs from malicious open-source packages. ★ 1,102 · 2026-08-24
- SonarQube MCP Server Analyze code quality and security with SonarQube Server or Cloud directly in AI assistants. ★ 632 · 2026-08-24
- Decionis MCP Server Fail-closed policy gate for AI agent actions, with local evaluation and native pre-tool hooks. ★ 533 · 2026-08-24
- HOL Guard Local-first AI agent security evidence and approval workflows through HOL Guard's stdio MCP server. ★ 470 · 2026-08-25
- Emisar Let AI operate servers without SSH. Choose actions, approve risky changes, and audit every step. ★ 409 · 2026-08-23
- Bradesco MCP server for Bradesco - Pix, Cobrança (boleto), Arrecadação, Extrato (OAuth2 + mTLS) ★ 269 · 2026-08-12
Pairs well with
Servers that cover what Calllint doesn't - only shown when the pairing reason fits the companion.
More security MCP servers · Cinderfi - Retirement Planning · Ethical Hacking · Btg · C6
More TypeScript MCP servers · Callosium · Agent Device (callstack) · Agent Device (callstackincubator) · Calypso Multimodal RAG MCP · Activitypub MCP · see all