Bartholomew AI Security Gate

Sub-35µs in-process AI agent security gate.

CommunityOnlineNo sign-inGlobalFreeRead-only

What it can do

  • Execute Database Query: Evaluates a SQL query through the Bartholomew AST invariant firewall before execution. Blocks DROP TABLE, TRUNCATE, and DELETE without WHERE clause in under 35 microseconds. Re
  • Execute System Command: Evaluates a shell command through the sub-35µs Bartholomew AST safety gate before execution. Blocks rm -rf, chmod 777, curl | bash, and privilege escalation patterns. Returns a
  • Btp Guard Eval: Generic pre-flight security evaluation for any proposed AI agent action — SQL queries, HTTP calls, file writes, or wire transfers. Never executes the action. Returns ALLOW or DENY with

What data it sees

Do you need an account

No: the server works without sign-in

Sub-35µs in-process AI agent security gate. Evaluates every tool call before execution - blocks rm -rf, DROP TABLE, secret exfiltration, and path traversal. Generates Ed25519 Merkle receipts for SOC 2 compliance.

How to connect

How to connect Bartholomew AI Security Gate to Claude

The server address to paste into Claude settings:

https://calls_10k--itsubsolomon.run.tools

  1. Open Claude (claude.ai or the desktop app).
  2. Go to Settings → Connectors.
  3. Click Add custom connector.
  4. Paste the server address copied below into Remote MCP server URL and click Add.
  5. In a chat, click + → Connectors and switch the new connector on.

Custom connectors are available on Free, Pro, Max, Team and Enterprise plans (Free is limited to one). On Team and Enterprise an organization Owner adds the connector first under Organization settings → Connectors.

Authorization

After you click Add, a sign-in window for the service opens. Sign in with your own account and approve access. Claude never sees your password.

How to connect Bartholomew AI Security Gate to ChatGPT

The server address to paste into ChatGPT settings:

https://calls_10k--itsubsolomon.run.tools

  1. Open ChatGPT in a browser (chatgpt.com). A Plus, Pro, Business, Enterprise or Edu plan is required.
  2. Turn on developer mode once: Settings → Apps → Advanced settings → Developer mode.
  3. Open Settings → Connectors and click Create.
  4. Fill in the form: Name (anything), Description (one line about what the service does), MCP server URL (copy it below).
  5. Under Authentication choose OAuth if the service requires sign-in, otherwise None. Click Create.
  6. In a new chat open + → Apps/Connectors and enable the connector.

OpenAI has renamed this section before (Connectors → Apps/Plugins). If the label differs, search settings for "developer mode". On Business/Enterprise workspaces an admin must allow custom connectors first.

Authorization

On first use ChatGPT opens the service's sign-in window. Sign in and approve access.

How to connect Bartholomew AI Security Gate to Cursor

The server address to paste into Cursor settings:

https://calls_10k--itsubsolomon.run.tools

Fastest: click Open in Cursor below and confirm the prompt.

Manually:

  1. In Cursor open Settings → Cursor Settings → MCP and click Add new global MCP server.
  2. Paste the JSON copied below into ~/.cursor/mcp.json (per project: .cursor/mcp.json in the repo root).
  3. Save the file. The server appears in the MCP list; authorize it there if asked.

Authorization

If the service needs sign-in, an authorize button appears next to the server in the MCP list.

Server tool list (3)

Raw names from tools/list. Only developers need these.

execute_database_queryEvaluates a SQL query through the Bartholomew AST invariant firewall before execution. Blocks DROP TABLE, TRUNCATE, and DELETE without WHERE clause in under 35 microseconds. Returns an Ed25519 Merkle receipt as auditable proof.
execute_system_commandEvaluates a shell command through the sub-35µs Bartholomew AST safety gate before execution. Blocks rm -rf, chmod 777, curl | bash, and privilege escalation patterns. Returns an Ed25519 Merkle receipt.
btp_guard_evalGeneric pre-flight security evaluation for any proposed AI agent action — SQL queries, HTTP calls, file writes, or wire transfers. Never executes the action. Returns ALLOW or DENY with a signed Merkle receipt. Safe to call on any input.