// SCAN REPORT

Local Dev Bridge MCP

14 tools. 6 can modify or destroy data without limits.

6 write tools that can modify data. Rate limits recommended.

Last updated: 4 Jul 2026

6 can modify or destroy data

8 read-only

14 tools total

Community server · catalogue entry verified 04/07/2026

How to control Local Dev Bridge MCP ↓

TOOL MAP

What Local Dev Bridge MCP exposes to your agents

Read (8) Write / Execute (6) Destructive / Financial (0)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

High Risk

The most dangerous Local Dev Bridge MCP tools

Execute · Critical run_command Shell command execution is inherently an Execute category risk because outcomes depend entirely on the command argument provided. Write · Medium uat_reset_test This tool modifies the state of a test (from claimed/completed back to pending), which is a reversible write operation. Write · High edit_file This tool modifies file contents through text replacement. Write · Medium uat_complete_test This tool creates or modifies data (test results) and moves files between directories (in-progress/ to results/), which are reversible write operations.

6 of Local Dev Bridge MCP's 14 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Local Dev Bridge MCP

PolicyLayer is an MCP gateway — it sits between your AI agents and Local Dev Bridge MCP, and nothing reaches the server without passing your rules. These are the rules we recommend:

Rate limit write operations

{
  "edit_file": {
    "limits": [
      {
        "counter": "edit_file_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "list_directory": {
    "limits": [
      {
        "counter": "list_directory_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register Local Dev Bridge MCP — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON LOCAL DEV BRIDGE →

Instant setup, no code required.

FULL CATALOGUE

All 14 Local Dev Bridge MCP tools

EXECUTE 1 tools

Execute run_command Execute a shell command in the projects directory. Use for running npm install, git commands, tests, etc.

WRITE 5 tools

Write edit_file Edit a file by replacing specific text. The old_text must match exactly (including whitespace). Write uat_claim_test Claim a pending test for execution. Moves it from pending/ to in-progress/ so other sessions don\ Write uat_complete_test Mark a test as completed with results. Moves it from in-progress/ to results/ and writes the outcome. Use this Write uat_reset_test Move a test back to pending (e.g. if it was claimed but never completed, or if you want to re-run it). Write write_file Create or overwrite a file with new content. Use this to create new files or completely replace existing ones.

READ 8 tools

Read list_directory List files and directories in a given path Read read_file Read the contents of a file from the local file system. Use this to view existing code files. Read search_files Search for text within files in a directory (recursive) Read uat_dashboard Get a summary dashboard of the UAT queue — counts of pending, in-progress, and completed tests broken down by Read uat_get_pending List all pending UAT tests waiting to be executed. Use this from the browser-side session to see what needs te Read uat_get_results Get test results. Use this from Claude Code to check how tests went after the browser session ran them. Read uat_get_test Read the full details of a specific UAT test by its ID. Read uat_queue_test Queue a new UAT test for browser execution. Writes a structured test file to the pending queue. Returns the te

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about Local Dev Bridge MCP

How do I prevent bulk modifications through Local Dev Bridge MCP? +

The Local Dev Bridge MCP server has 5 write tools including edit_file, uat_claim_test, uat_complete_test. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Local Dev Bridge MCP.

How many tools does the Local Dev Bridge MCP server expose? +

14 tools across 4 categories: Destructive, Execute, Read, Write. 8 are read-only. 6 can modify, create, or delete data.

How do I enforce a policy on Local Dev Bridge MCP? +

Register the Local Dev Bridge MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Local Dev Bridge MCP tool call.

Deterministic rules across all 14 Local Dev Bridge MCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON LOCAL DEV BRIDGE →

Instant setup, no code required.

14 Local Dev Bridge MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.