🚀 Enhanced local context with deterministic query-aware retrieval, AST-grep, and actionable intelligence. Provides: (1) deterministic AnswerDraft, (2) ranked JumpTargets, (3) tight MiniBundle (≤3k tokens), (4) NextActions—all using AST + static heuristics. Optional embedding enhancement when ava...
AI agents call local_context to retrieve information from Ambiance MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool performs semantic analysis, AST parsing, and context retrieval on codebases—all read operations that extract and present information. There are no mentions of code execution, data modification, deletion, or financial operations. The deterministic nature and focus on 'insights' and 'actionable intelligence' confirm this is informational retrieval.
From the tool's definition Tool provides retrieval and analysis capabilities: 'deterministic query-aware retrieval', 'ranked JumpTargets', 'AnswerDraft', and 'MiniBundle' extraction.
Attacks that exploit this kind of access
🚀 Enhanced local context with deterministic query-aware retrieval, AST-grep, and actionable intelligence. Provides: (1) deterministic AnswerDraft, (2) ranked JumpTargets, (3) tight MiniBundle (≤3k tokens), (4) NextActions—all using AST + static heuristics. Optional embedding enhancement when available. Completely offline with zero external dependencies for core functionality. It is categorised as a Read tool in the Ambiance MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Ambiance MCP Server MCP server in PolicyLayer and add a rule for local_context: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Ambiance MCP Server. Nothing to install.
local_context is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the local_context rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for local_context. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
local_context is provided by the Ambiance MCP Server MCP server (sbarron/ambiancemcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
local_context is one line of Ambiance MCP Server's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →