# retrieve_memory

Retrieve the top-k memories most similar to the query.

Agent View of the PolicyLayer registry record for `retrieve_memory`. HTML page: https://policylayer.com/tools/ashlesh-t-cognirepo/retrieve-memory

## Facts

- Tool: `retrieve_memory`
- Server: CogniRepo (`pypi:cognirepo`) — https://policylayer.com/tools/ashlesh-t-cognirepo.md
- Install: `npx -y pypi:cognirepo`
- Homepage: https://github.com/ashlesh-t/cognirepo
- Risk category: Read (Low risk)
- Registry record: grade A, identity unverified
- Server rate-limited: no
- Parameters: 0
- Recommended policy verdict: Allowed

## Example call (MCP tools/call, JSON-RPC 2.0)

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "retrieve_memory",
    "arguments": {}
  }
}
```

## Why retrieve_memory is rated Low

This tool queries an existing memory store and returns results based on similarity matching. It has no side effects, does not modify data, execute code, delete records, or perform financial operations. It is a straightforward read operation that retrieves information from persistent memory without altering it.

From the tool's own definition: "Tool name is 'retrieve_memory' and description states 'Retrieve the top-k memories most similar to the query.' The verb 'retrieve' and the read-only nature of querying a memory store with no modification or execution describe a data retrieval operation."

## Use case

AI agents call retrieve_memory to retrieve information from CogniRepo without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

## Recommended policy (PolicyLayer)

Verdict: **Allowed**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches CogniRepo:

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "retrieve_memory": {}
  }
}
```

## Other tools on CogniRepo (33)

- `supersede_learning` — Other — https://policylayer.com/tools/ashlesh-t-cognirepo/supersede-learning.md
- `architecture_overview` — Read — https://policylayer.com/tools/ashlesh-t-cognirepo/architecture-overview.md
- `context_pack` — Read — https://policylayer.com/tools/ashlesh-t-cognirepo/context-pack.md
- `cross_repo_search` — Read — https://policylayer.com/tools/ashlesh-t-cognirepo/cross-repo-search.md
- `cross_repo_traverse` — Read — https://policylayer.com/tools/ashlesh-t-cognirepo/cross-repo-traverse.md
- `dependency_graph` — Read — https://policylayer.com/tools/ashlesh-t-cognirepo/dependency-graph.md
- `episodic_search` — Read — https://policylayer.com/tools/ashlesh-t-cognirepo/episodic-search.md
- `explain_change` — Read — https://policylayer.com/tools/ashlesh-t-cognirepo/explain-change.md
- `find_symbol_path` — Read — https://policylayer.com/tools/ashlesh-t-cognirepo/find-symbol-path.md
- `get_agent_bootstrap` — Read — https://policylayer.com/tools/ashlesh-t-cognirepo/get-agent-bootstrap.md
- `get_error_patterns` — Read — https://policylayer.com/tools/ashlesh-t-cognirepo/get-error-patterns.md
- `get_last_context` — Read — https://policylayer.com/tools/ashlesh-t-cognirepo/get-last-context.md
- `get_service_endpoints` — Read — https://policylayer.com/tools/ashlesh-t-cognirepo/get-service-endpoints.md
- `get_session_brief` — Read — https://policylayer.com/tools/ashlesh-t-cognirepo/get-session-brief.md
- `get_session_history` — Read — https://policylayer.com/tools/ashlesh-t-cognirepo/get-session-history.md
- `get_user_profile` — Read — https://policylayer.com/tools/ashlesh-t-cognirepo/get-user-profile.md
- `graph_stats` — Read — https://policylayer.com/tools/ashlesh-t-cognirepo/graph-stats.md
- `list_org_context` — Read — https://policylayer.com/tools/ashlesh-t-cognirepo/list-org-context.md
- `lookup_symbol` — Read — https://policylayer.com/tools/ashlesh-t-cognirepo/lookup-symbol.md
- `org_dependencies` — Read — https://policylayer.com/tools/ashlesh-t-cognirepo/org-dependencies.md
- `org_search` — Read — https://policylayer.com/tools/ashlesh-t-cognirepo/org-search.md
- `org_wide_search` — Read — https://policylayer.com/tools/ashlesh-t-cognirepo/org-wide-search.md
- `search_docs` — Read — https://policylayer.com/tools/ashlesh-t-cognirepo/search-docs.md
- `search_token` — Read — https://policylayer.com/tools/ashlesh-t-cognirepo/search-token.md
- `semantic_search_code` — Read — https://policylayer.com/tools/ashlesh-t-cognirepo/semantic-search-code.md
- `subgraph` — Read — https://policylayer.com/tools/ashlesh-t-cognirepo/subgraph.md
- `who_calls` — Read — https://policylayer.com/tools/ashlesh-t-cognirepo/who-calls.md
- `link_repos` — Write — https://policylayer.com/tools/ashlesh-t-cognirepo/link-repos.md
- `log_episode` — Write — https://policylayer.com/tools/ashlesh-t-cognirepo/log-episode.md
- `record_decision` — Write — https://policylayer.com/tools/ashlesh-t-cognirepo/record-decision.md
- …and 3 more: https://policylayer.com/tools/ashlesh-t-cognirepo.md

## For agents

This record is a snapshot. Live verdicts and the full registry:

- Check every server in your MCP config at once: `npx -y policylayer stack`
- Vet a server before you add it: install the mcp-precheck skill — `npx skills add https://policylayer.com` (skill text: https://policylayer.com/skill.md)
- Query the registry over MCP: endpoint `https://api.policylayer.com/mcp` — tools `check_mcp_server`, `check_mcp_stack`, `check_tool`, `search_registry`, `get_change_events`

---

Source: the PolicyLayer MCP registry — one continuously verified record per MCP server. Full record: https://policylayer.com/registry?q=ashlesh-t-cognirepo · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/ashlesh-t-cognirepo