AI agents use context_link to create or update resources in MCP Memory Keeper — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MCP Memory Keeper environment.
The tool creates new relationships/metadata (a reversible modification) between context items in the persistent storage system. It does not execute external code, delete data, involve financial transactions, or retrieve data without side effects.
From the tool's definition Tool name 'context_link' with description 'Create a relationship between two context items' indicates a write operation that creates or modifies metadata linking two existing context entries. This is reversible (the link can be removed or modified later).
Documented attack patterns abuse exactly the kind of access context_link gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MCP Memory Keeper, and nothing reaches the server without passing your rules. This is the rule we recommend for context_link:
{
"version": "1",
"default": "deny",
"tools": {
"context_link": {
"limits": [
{
"counter": "context_link_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}context_link stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Create a relationship between two context items. It is categorised as a Write tool in the MCP Memory Keeper MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the MCP Memory Keeper MCP server in PolicyLayer and add a rule for context_link: 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 MCP Memory Keeper. Nothing to install.
context_link is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the context_link 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 context_link. 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.
context_link is provided by the MCP Memory Keeper MCP server (mkreyman/mcp-memory-keeper). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from MCP Memory Keeper, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
40 MCP Memory Keeper tools catalogued and risk-classified — across an index of 43,000+ MCP servers.