Captures the user's project architecture to inform i18n implementation strategy. When to Use Called during i18n_checklist Step 1. The checklist tool will tell you when to call this. If you're implementing i18n: 1. Call i18n_checklist(step_number=1, done=false) FIRST 2. The checklist will instruct...
Part of the Main server.
Free to start. No card required.
AI agents call get_project_context to retrieve information from Main without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions -- but you may still want rate limits to control API costs.
Even though get_project_context only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.
Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.
{
"version": "1",
"default": "deny",
"tools": {
"get_project_context": {}
}
}See the full Main policy for all 4 tools.
These attack patterns abuse exactly the kind of access get_project_context gives an agent. Each links to the full case and the policy that stops it:
Other read tools across the catalogue. The same approach applies to each: allow, with a rate cap to control cost.
Captures the user's project architecture to inform i18n implementation strategy. When to Use Called during i18n_checklist Step 1. The checklist tool will tell you when to call this. If you're implementing i18n: 1. Call i18n_checklist(step_number=1, done=false) FIRST 2. The checklist will instruct you to call THIS tool 3. Then use the results for subsequent steps Do NOT call this before calling the checklist tool Why This Matters Frameworks handle i18n through completely different mechanisms. The same outcome (locale-aware routing) requires different code for Next.js vs TanStack Start vs React Router. Without accurate detection, you'll implement patterns that don't work. How to Use 1. Examine the user's project files (package.json, directories, config files) 2. Identify framework markers and version 3. Construct a detectionResults object matching the schema 4. Call this tool with your findings 5. Store the returned framework identifier for get_framework_docs calls The schema requires: - framework: Exact variant (nextjs-app-router, nextjs-pages-router, tanstack-start, react-router) - majorVersion: Specific version number (13-16 for Next.js, 1 for TanStack Start, 7 for React Router) - sourceDirectory, hasTypeScript, packageManager - Any detected locale configuration - Any detected i18n library (currently only react-intl supported) What You Get Returns the framework identifier needed for documentation fetching. The 'framework' field in the response is the exact string you'll use with get_framework_docs.. It is categorised as a Read tool in the Main MCP Server, which means it retrieves data without modifying state.
Register the Main MCP server in PolicyLayer and add a rule for get_project_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 Main. Nothing to install.
get_project_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 get_project_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 get_project_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.
get_project_context is provided by the Main MCP server (https://mcp.lingo.dev/main). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 4 Main tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4,600+ MCP servers and 31,000+ tools scanned and risk-classified.