Search memories by graph entity (file path, class name, method, SDK, error type). Use when user asks 'what did we do with X', 'memories about file Y', or 'recall related to UserService'. Same entity types as IDE extraction: file, class, method, sdk, config_key, error_type, etc. Returns direct + r...
AI agents call search_memory_graph to retrieve information from Memoryx without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
limit | number | — | Max results, default 5 |
query | string | — | Optional. Extra keywords; if empty, entity_name is used as query |
entity_name | string | Yes | Entity to expand (e.g. file path, class name, method name) |
time_filter | object | — | Optional. start/end YYYY-MM-DD |
Parameters from the server's own tool schema.
This is a retrieval operation that queries and returns information about stored memories based on entity filters (file path, class name, method, etc.). It has no side effects, does not modify, delete, or execute anything—purely informational. Low severity due to read-only nature with limited blast radius if misused.
From the tool's definition Tool performs search/query operations on stored memories by graph entity with no modification capability—'Search memories by graph entity', 'Returns direct + related memories'.
Risk signalsAccepts freeform code/query input (query)
Attacks that exploit this kind of access
Search memories by graph entity (file path, class name, method, SDK, error type). Use when user asks 'what did we do with X', 'memories about file Y', or 'recall related to UserService'. Same entity types as IDE extraction: file, class, method, sdk, config_key, error_type, etc. Returns direct + related memories. time_filter uses absolute dates (YYYY-MM-DD). It is categorised as a Read tool in the Memoryx MCP Server, which means it retrieves data without modifying state.
search_memory_graph accepts 4 parameters: limit, query, entity_name, time_filter. Required: entity_name. The full parameter table on this page comes from the server's own tool schema.
Register the Memoryx MCP server in PolicyLayer and add a rule for search_memory_graph: 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 Memoryx. Nothing to install.
search_memory_graph 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 search_memory_graph 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 search_memory_graph. 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.
search_memory_graph is provided by the Memoryx MCP server (@t0ken.ai/memoryx-mcp-server). 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 →