Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    Judikt MCP Security

    1

    Your AI agent can call every tool an MCP server exposes, including the ones that delete, overwrite or deploy.

    Free

    Security scanned
    Judikt MCP Security

    Judikt MCP Security

    Example session with this skill installed

    Put Judikt in front of my filesystem MCP server for ~/project so Claude Code can only read files there, then prove it works.

    • Read your context and instructions
    • Compiled the judikt mcp security

    Judikt is now guarding your filesystem server. Claude Code can read files under ~/project, every write tool is hidden and blocked, and the audit trail verifies.

    1. Environment check (read-only)

    python3 scripts/diagnose.py found Python 3.13 and

    judikt 0.3.0. It reported "network_calls": false and "config_contents_read": false, so nothing was changed.

    2. Starter policy, generated from the server's real tools

    With your approval I ran

    judikt init --name filesystem --output ~/project/judikt-policy.json -- \
      npx -y @modelcontextprotocol/server-filesystem ~/project
    
    Judikt starter policy (read-only): read=10 write=1 destructive=3
    Excluded tools: write_file, edit_file, create_directory, move_file
    Approval-gated tools: none
    Annotation/name conflicts: none
    

    3. Client configuration (the change you approved in .mcp.json)

    {
      "mcpServers": {
        "filesystem": {
          "command": "judikt",
          "args": ["wrap", "--policy", "/Users/you/project/judikt-policy.json", "--name", "filesystem", "--",
                   "npx", "-y", "@modelcontextprotocol/server-filesystem", "/Users/you/project"]
        }
      }
    }
    

    4. Smoke test

    CheckResult
    tools/list10 tools, all read-only (read_text_file, list_directory, search_files, ...)
    read_text_file docs/runbook.mdALLOW, returned the file's contents
    write_file docs/runbook.md (the denial check you authorized)DENY before reaching the server: tool 'write_file' is not allowlisted for 'filesystem' (rule: allowlist). The file is unchanged.
    judikt audit verify"status": "valid", "signed": true, 2 events checked

    5. Assessment

    ControlStatusEvidence
    Least-privilege tool exposureverified10 of 14 tools exposed; all 4 write tools absent from tools/list
    Pre-execution denialverifiedwrite_file refused with rule allowlist; file unchanged
    Tool-definition pinningverifiedPin store active; the 4 excluded tools await review with judikt pins accept
    Signed, hash-chained auditverifiedjudikt audit verify: valid, signed
    Response inspectionconfigured-not-verifiedOn by default; no malicious content was tested
    Approval tokensnot-applicableRead-only profile, so no approval-gated tools
    Remote authenticationnot-applicableLocal stdio only
    Tamper evidence against a local attackernot-configuredNo external checkpoint destination such as S3 Object Lock or a SIEM

    Next steps

    1. Restart Claude Code and confirm the filesystem server shows 10 tools.
    2. If the agent should edit files, rerun judikt init with --profile approve-writes so every write needs a signed, single-use approval.
    3. For audit evidence that survives a compromised machine, export checkpoints with judikt audit checkpoint --output s3://....

    Connects securely to your tools. The creator never sees your data.

    About this skill

    Your AI agent can call every tool an MCP server exposes, including the ones that delete, overwrite or deploy. This skill puts Judikt, an open-source security gateway, between your agent and that server, and walks your agent through setting it up safely, asking for your consent at every step that changes anything.

    What it does

    • Generates a least-privilege policy from the server's real tool list. Read-only by default: tools that write, edit, move or delete are hidden from the agent. The approve-writes profile exposes them behind human-signed, single-use approvals.
    • Connects Claude Code or Cursor by proposing a minimal change to .mcp.json or .cursor/mcp.json and leaving your other servers untouched.
    • Smoke-tests the gateway with tools/list and one read-only call you authorize. It never uses a mutating tool just to prove connectivity.
    • Produces an evidence-based assessment that marks each control as verified, configured-not-verified, not-configured or not-applicable, so configuration is never mistaken for proof.
    • Troubleshoots policy, identity, approval, pinning and audit failures without weakening security to make a test pass. When Judikt holds a call, the skill tells you the judikt approve <id> command to run yourself; it never approves on your behalf.

    What Judikt enforces once it's in place

    • Allowlists and argument checks before any tool runs
    • New in 0.4.0: a provenance gate that holds a write reusing an address, account, link or ID that an instruction in tool output asked for, until you approve it with one command (judikt approve <id>)
    • New in 0.4.0: task scopes (judikt wrap --task-writes send_email) that hold any write the task didn't declare
    • Tool-definition pinning: a server that silently changes a tool is refused at startup
    • Kill switches, rate limits and circuit breakers
    • Redaction of secrets in results and audit logs
    • A hash-chained, HMAC-signed audit trail you can check with judikt audit verify

    Honest limits

    All figures below come from replaying each benchmark's own correct tool calls, assuming an agent that obeys every injection. No language model ran, so they are not end-to-end agent results.

    • In an InjecAgent replay, 0 of 1,054 harmful actions executed under the read-only or approve-writes profiles.
    • On AgentDyn, a benchmark Judikt was never developed against, the provenance gate held 67.8% of attacks and provenance plus a task scope held 94.8%. 27 of 60 legitimate tasks would stop for one approval, mostly tasks that act on instructions in emails or web pages.
    • Prompt-injection detection is a tripwire, not the main defence: it caught 54.8% of BIPIA and 7.6% of InjecAgent attacks with no false positives.

    The skill does not bundle or silently install Judikt, edit client configuration without your consent, or invent approval tokens.

    Requirements

    Python 3.11+ and the Judikt runtime, installed separately with pip install "judikt==0.4.0". Upgrading from 0.3.0? The provenance gate is on by default; read the upgrade notes: https://github.com/gaurav-gs7/Judikt/blob/v0.4.0/CHANGELOG.md. Open source under Apache-2.0: https://github.com/gaurav-gs7/Judikt

    Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Security.

    Requires Python 3.11+ and a separately installed Judikt runtime (pip install judikt). Never installs software, edits client configuration, or handles credentials without your consent. Smoke tests use read-only tools only. Only Claude Code and Cursor are qualified clients. Judikt's prompt-injection scanning is a heuristic tripwire: on independent benchmarks it caught 0.8% (BIPIA) and 0% (InjecAgent) of attacks, so the real protection comes from policy, approvals and pinning.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before buying a skill.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Free to use

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 19 days ago

    • Free with an Agensi account

    Software
    Python 3.11+judikt 0.4.0MCP server to protect

    Install with pip install judikt==0.4.0. The server can be stdio or a remote Streamable HTTP endpoint.

    Permissions

    Terminal / Shell
    Read Files
    Write Files
    Network Access

    File Scopes

    .mcp.json
    .cursor/mcp.json
    *-policy.json

    Terminal runs the read-only diagnostic and, only with your consent, judikt init and judikt wrap. Read Files inspects candidate client-configuration paths and the generated policy. Write Files creates the policy file and, after you approve a shown diff, edits .mcp.json or .cursor/mcp.json. Network access is used only if you agree to install Judikt with pip or to test a remote Judikt endpoint. The bundled diagnostic makes no network calls and reads no environment values.

    Listed22 days ago
    Updated19 days ago

    What's inside

    Frequently Asked Questions

    It puts the Judikt gateway between your agent and the MCP server. Judikt reads the server's real tool list and generates a read-only policy by default, so tools that write, edit, move or delete are hidden and blocked before they run. If you choose the approve-writes profile, those tools need a human-signed, single-use approval token. Tool definitions are pinned, and every decision is recorded in a signed, hash-chained audit trail.

    Claude Code (2.1.308) and Cursor Agent (2026.10.19) are qualified on macOS and Linux, using .mcp.json and .cursor/mcp.json. Other clients that accept standard mcpServers stdio entries may work, but they are not tested. Judikt can wrap local stdio servers and, when you run it as a separate service, protect authenticated remote Streamable HTTP endpoints.

    Yes. The skill runs a read-only environment check, then a smoke test through the gateway: it lists the exposed tools, makes one read-only call you authorize, and confirms a disallowed call is refused before it reaches the server. It finishes with judikt audit verify. It never uses a mutating tool just to prove connectivity.

    No. The skill does not bundle Judikt; you install it with pip install judikt. The agent shows you each command and every proposed change to your client configuration as a diff, and asks before installing anything, launching the server, writing the policy, or editing a config file. It never invents approval tokens or weakens a control to make a test pass.

    Each control is marked verified, configured-not-verified, not-configured or not-applicable, with sanitized evidence such as the exposed tool list, the rule that refused a call, and the audit verification result. It also lists unresolved gaps and the exact scope tested, so configuration alone is never reported as a passing control.

    New in Security

    Free