context

Get full context about a topic: the entity, its observations, relationships, and related entities. Follows relationship graph to discover connected information.

ServerHippocampus
CategoryRead

How to control context ↓

WHAT IT DOES

What context does on Hippocampus

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

THE RISK

Low Risk

Why context needs a policy

This tool performs a query operation that retrieves and assembles existing data from a knowledge graph without modifying, creating, or deleting any information. The ability to traverse relationships and discover connected information is a read-only operation. While it accesses a memory/context store, there is no side effect or irreversible action, making it a classic Read category tool with low severity.

From the tool's definition Tool retrieves context about a topic by following relationship graphs to discover connected information. Uses verbs like 'Get' and 'discover' indicating data retrieval with no modification or deletion capability.

Documented attack patterns abuse exactly the kind of access context gives an agent:

POLICY

How to control context

PolicyLayer is an MCP gateway — it sits between your AI agents and Hippocampus, and nothing reaches the server without passing your rules. This is the rule we recommend for context:

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "context": {}
  }
}

context is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.

Create a free account and register Hippocampus — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

CAP THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More Hippocampus tools

Destructive forget Delete a specific memory or an entire entity and all its associated data. Use with care — Destructive merge_entities Merge multiple entities into one. Moves all observations, embeddings, and relationships fr Write merge Merge multiple observations into one. Atomic operation: provide merged text + list of obse Write onboard Bootstrap memory from the current AI session. Returns extraction instructions — follow the Write remember Store a memory or piece of information. Use this to save facts, preferences, decisions, re Write update Replace an existing observation with new content. Finds the old observation by exact conte Read check_version Check if cached entity content is still current. Pass a previously received version_hash t Read recall Search memories by semantic similarity and keyword match. Returns relevant stored informat

All 11 Hippocampus tools →

Read tools on other servers

M-Team MCP Server get_torrent_detail YouTube MCP Server search_channel Android Forensics ADB MCP Server parse_browser_history 0xarchive web3_challenge

Go deeper

The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Data exfiltration → How read access becomes an exfiltration channel when chained with untrusted content.
MCP token cost → What connecting this server costs in context-window tokens on every request.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about context

What does the context tool do? +

Get full context about a topic: the entity, its observations, relationships, and related entities. Follows relationship graph to discover connected information. It is categorised as a Read tool in the Hippocampus MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on context? +

Register the Hippocampus MCP server in PolicyLayer and add a rule for 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 Hippocampus. Nothing to install.

What risk level is context? +

context is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit context? +

Yes. Add a rate_limit block to the 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.

How do I block context completely? +

Set action: deny in the PolicyLayer policy for 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.

What MCP server provides context? +

context is provided by the Hippocampus MCP server (karrolcia/hippocampus). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Hippocampus tool call.

Start from Hippocampus, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →

Free to start. No card required.

11 Hippocampus tools catalogued and risk-classified — across an index of 43,000+ MCP servers.