v3.1.0 M2: Append one observation or goal to working memory
AI agents use working_add to create or update resources in Codevira MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Codevira MCP environment.
This tool creates or modifies data (appends to working memory) without permanently deleting or overwriting existing data, making it a Write operation. Severity is medium because misuse could introduce incorrect observations or goals into the shared knowledge base used by the AI agent, potentially affecting decision-making across sessions, but the operation remains reversible (appended data can be corrected or…
From the tool's definition Tool name 'working_add' and description 'Append one observation or goal to working memory' indicate data modification. The verb 'append' explicitly describes creating and adding new data to a persistent memory store.
Documented attack patterns abuse exactly the kind of access working_add gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Codevira MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for working_add:
{
"version": "1",
"default": "deny",
"tools": {
"working_add": {
"limits": [
{
"counter": "working_add_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}working_add 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.
v3.1.0 M2: Append one observation or goal to working memory. It is categorised as a Write tool in the Codevira MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Codevira MCP server in PolicyLayer and add a rule for working_add: 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 Codevira MCP. Nothing to install.
working_add 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 working_add 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 working_add. 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.
working_add is provided by the Codevira MCP server (sachinshelke/codevira). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Codevira MCP, 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.
48 Codevira MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.