Ejecuta mantenimiento en la base de datos SQLite: integrity_check para detectar corrupción y wal_checkpoint para consolidar el WAL al archivo principal. Devuelve {integrity_ok, integrity_errors[], wal_checkpoint: {busy, log, checkpointed}}.
AI agents invoke db_maintenance to trigger actions in Engram. 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 database maintenance operations (integrity check and WAL checkpoint). The WAL checkpoint consolidates the write-ahead log into the main database file, which is a system-level operation with side effects on database internals. While not destructive in the data-deletion sense, it actively modifies the database file structure and is not a simple read.
From the tool's definition 'Ejecuta mantenimiento en la base de datos SQLite: integrity_check para detectar corrupción y wal_checkpoint para consolidar el WAL al archivo principal' — runs database maintenance operations including WAL checkpoint which modifies database internals
Attacks that exploit this kind of access
Ejecuta mantenimiento en la base de datos SQLite: integrity_check para detectar corrupción y wal_checkpoint para consolidar el WAL al archivo principal. Devuelve {integrity_ok, integrity_errors[], wal_checkpoint: {busy, log, checkpointed}}. It is categorised as a Execute tool in the Engram MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Engram MCP server in PolicyLayer and add a rule for db_maintenance: 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 Engram. Nothing to install.
db_maintenance 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 db_maintenance 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 db_maintenance. 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.
db_maintenance is provided by the Engram MCP server (jacksini/engram-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →