// SCAN REPORT

Ambiance MCP Server

24 tools. 7 can modify or destroy data without limits.

1 destructive tool with no built-in limits. Policy required.

Last updated: 29 Jun 2026

7 can modify or destroy data

17 read-only

24 tools total

Community server · catalogue entry verified 29/06/2026

How to control Ambiance MCP Server ↓

TOOL MAP

What Ambiance MCP Server exposes to your agents

Read (17) Write / Execute (6) Destructive / Financial (1)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Ambiance MCP Server tools

Destructive · High ambiance_reset_indexes This tool performs irreversible deletion of data (indexes) without the ability to undo the action. Execute · Medium ambiance_start_watching This tool executes a file-watching daemon/process that continuously monitors a directory and triggers indexing operations. Execute · Low ambiance_stop_watching The tool executes an operation (stopping a watch process) whose effects depend on which project is specified as an argument. Execute · Medium ambiance_auto_detect_index This tool triggers an active operation—detecting the current project and initiating an indexing process.

7 of Ambiance MCP Server's 24 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Ambiance MCP Server

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

Deny destructive operations

{
  "ambiance_reset_indexes": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations

{
  "ambiance_index_project": {
    "limits": [
      {
        "counter": "ambiance_index_project_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "ai_code_explanation": {
    "limits": [
      {
        "counter": "ai_code_explanation_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 Ambiance MCP Server — 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 AMBIANCE →

Instant setup, no code required.

FULL CATALOGUE

All 24 Ambiance MCP Server tools

DESTRUCTIVE 1 tools

Destructive ambiance_reset_indexes Delete/reset all indexes for a project (both local and cloud)

EXECUTE 3 tools

Execute ambiance_auto_detect_index Automatically detect current project and start indexing if user has API key Execute ambiance_start_watching Start watching a project for file changes (automatic incremental indexing) Execute ambiance_stop_watching Stop watching a project for file changes

WRITE 3 tools

Write ambiance_index_project Index a project with smart ignore patterns and change detection Write ambiance_setup_project ⚙️ SETUP PROJECT - Auto-detect, index, and configure project for optimal context retrieval. Handles all the b Write manage_embeddings Coordinate embedding lifecycle and workspace configuration with a single entry point. Workspace Actions - get

READ 17 tools

Read ai_code_explanation 📚 AI-POWERED CODE EXPLANATION AND DOCUMENTATION Accepts absolute paths or relative paths (when workspace can Read ai_debug 🤖 AI-powered debug analysis and fix suggestions When to use: - After gathering debug context with local_debu Read ai_get_context 🤖 AI-POWERED INTELLIGENT CONTEXT WITH STRUCTURED OUTPUT Accepts absolute paths or relative paths (when works Read ai_project_insights 🔍 AI-ENHANCED PROJECT INSIGHTS AND RECOMMENDATIONS Accepts absolute paths or relative paths (when workspace Read ambiance_get_context 🔍📦 GITHUB REPOSITORY CONTEXT GENERATION - Get comprehensive context bundle from your GitHub repositories usi Read ambiance_get_graph_context 🕸️📦 GRAPH-BASED REPOSITORY CONTEXT - Get intelligent context using graph-based retrieval with code relations Read ambiance_get_indexing_status Get status of active indexing sessions Read ambiance_list_github_repos 🐙 List GitHub repositories available through the Ambiance GitHub App integration Read ambiance_project_status 📊 PROJECT STATUS - Check indexing status, health, and configuration. Shows what Read ambiance_remote_query Remote query by projectId using the Ambiance cloud retrieval service. Read ambiance_search_github_repos 🐙 Search GitHub repositories indexed via Ambiance GitHub App - searches code from a specific GitHub repositor Read frontend_insights 🔍 Map routes, components, data flow, design system, and risks in the web layer with embedding-enhanced analys Read local_context 🚀 Enhanced local context with deterministic query-aware retrieval, AST-grep, and actionable intelligence. Pro Read local_debug_context 🐛 Gather comprehensive debug context from error logs and codebase analysis with focused embedding enhancement Read local_file_summary 📄 Get quick AST-based summary and key symbols for any file. Fast file analysis without external dependencies. Read local_project_hints 📊 Generate intelligent project navigation hints with word clouds, folder analysis, and architecture detection Read workspace_config ⚠️ DEPRECATED: Use manage_embeddings instead. This tool has been merged into manage_embeddings for unified wor

EXPLORE

Related servers

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

FAQ

Questions about Ambiance MCP Server

Can an AI agent delete data through the Ambiance MCP Server MCP server? +

Yes. The Ambiance MCP Server server exposes 1 destructive tools including ambiance_reset_indexes. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through Ambiance MCP Server? +

The Ambiance MCP Server server has 3 write tools including ambiance_index_project, ambiance_setup_project, manage_embeddings. 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 Ambiance MCP Server.

How many tools does the Ambiance MCP Server MCP server expose? +

24 tools across 4 categories: Destructive, Execute, Read, Write. 17 are read-only. 7 can modify, create, or delete data.

How do I enforce a policy on Ambiance MCP Server? +

Register the Ambiance MCP Server 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 Ambiance MCP Server tool call.

Deterministic rules across all 24 Ambiance MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON AMBIANCE →

Instant setup, no code required.

24 Ambiance MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.