Build intelligence database from codebase (one-time setup, ~30-60s). Required before using predict_coding_approach, get_project_blueprint, or get_pattern_recommendations. Re-run with force=true if codebase has significant changes. Most users should use auto_learn_if_needed instead - it runs this ...
AI agents invoke learn_codebase_intelligence to trigger actions in In Memoria. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool executes an automated codebase analysis and database-building operation. While it doesn't delete data (not Destructive) or create user-facing modifications (not Write), it runs a non-trivial computational process with observable side effects (populating an intelligence database).
From the tool's definition Tool 'learns' from codebase by building an intelligence database, requiring ~30-60s processing time with parameters like force=true suggesting it executes an analysis/indexing operation.
Documented attack patterns abuse exactly the kind of access learn_codebase_intelligence gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and In Memoria, and nothing reaches the server without passing your rules. This is the rule we recommend for learn_codebase_intelligence:
{
"version": "1",
"default": "deny",
"tools": {
"learn_codebase_intelligence": {
"limits": [
{
"counter": "learn_codebase_intelligence_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}learn_codebase_intelligence stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Build intelligence database from codebase (one-time setup, ~30-60s). Required before using predict_coding_approach, get_project_blueprint, or get_pattern_recommendations. Re-run with force=true if codebase has significant changes. Most users should use auto_learn_if_needed instead - it runs this automatically when needed. It is categorised as a Execute tool in the In Memoria MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the In Memoria MCP server in PolicyLayer and add a rule for learn_codebase_intelligence: 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 In Memoria. Nothing to install.
learn_codebase_intelligence is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the learn_codebase_intelligence 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 learn_codebase_intelligence. 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.
learn_codebase_intelligence is provided by the In Memoria MCP server (pi22by7/in-memoria). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 14 In Memoria tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
14 In Memoria tools catalogued and risk-classified — across an index of 42,500+ MCP servers.