Load sources into the Gemini context cache. Supports local directories, files, and GitHub repos (public/private). Use
AI agents use context_load to create or update resources in Mnemo — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mnemo environment.
This tool creates/writes new entries into a context cache (a reversible operation — cache entries can be evicted as indicated by the sibling 'context_evict' tool). It ingests external sources (local files, directories, GitHub repos) into the cache system, which is a write/create action. It doesn't execute code or irreversibly destroy data, so Write is the most appropriate category.
From the tool's definition Load sources into the Gemini context cache. Supports local directories, files, and GitHub repos (public/private).
Documented attack patterns abuse exactly the kind of access context_load gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Mnemo, and nothing reaches the server without passing your rules. This is the rule we recommend for context_load:
{
"version": "1",
"default": "deny",
"tools": {
"context_load": {
"limits": [
{
"counter": "context_load_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}context_load 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.
Load sources into the Gemini context cache. Supports local directories, files, and GitHub repos (public/private). Use. It is categorised as a Write tool in the Mnemo MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mnemo MCP server in PolicyLayer and add a rule for context_load: 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 Mnemo. Nothing to install.
context_load 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_load 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_load. 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_load is provided by the Mnemo MCP server (logos-flux/mnemo). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Mnemo, 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.
6 Mnemo tools catalogued and risk-classified — across an index of 43,000+ MCP servers.