tengu_copilot_universe
The ENTIRE scored universe in one call (limit=0 = all ~13k names), ranked, each with the model's absolute suggested_position_pct AND a relative normalized_weight that sums to ~100% across the returned set. Pass tickers=AAPL,NVDA,… to score+SIZE a specific holdings basket (the per-holding rebalanc...
This record as markdown: /tools/tengu-mcp/tengu-copilot-universe.md
What tengu_copilot_universe does on Tengu
AI agents use tengu_copilot_universe to create or update resources in Tengu, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Tengu environment.
| Parameter | Type | Required | Description |
|---|---|---|---|
side | string | — | |
limit | integer | — | |
tickers | string | — | |
normalize | boolean | — | |
max_weight | number | — | |
min_decile | integer | — |
Parameters from the server's own tool schema.
Why tengu_copilot_universe is rated Medium
An AI agent can call tengu_copilot_universe faster than any human can review: one bad instruction and it creates or modifies resources in Tengu by the hundred, each call as confident as the last.
Attacks that exploit this kind of access
The rule that runs tengu_copilot_universe safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Tengu, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For tengu_copilot_universe, this is the rule to start with:
tengu_copilot_universe 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.
The button opens the PolicyLayer dashboard: create your workspace, connect Tengu, apply this rule, and every tengu_copilot_universe call is checked against it from then on.
Questions about tengu_copilot_universe
The ENTIRE scored universe in one call (limit=0 = all ~13k names), ranked, each with the model's absolute suggested_position_pct AND a relative normalized_weight that sums to ~100% across the returned set. Pass tickers=AAPL,NVDA,… to score+SIZE a specific holdings basket (the per-holding rebalance path); omit it to screen/rank the universe (limit/min_decile/side). Use normalized_weight for rebalance targets. It is categorised as a Write tool in the Tengu MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
tengu_copilot_universe accepts 6 parameters: side, limit, tickers, normalize, max_weight, min_decile. The full parameter table on this page comes from the server's own tool schema.
Register the Tengu MCP server in PolicyLayer and add a rule for tengu_copilot_universe: 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 Tengu. Nothing to install.
tengu_copilot_universe 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 tengu_copilot_universe 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 tengu_copilot_universe. 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.
tengu_copilot_universe is provided by the Tengu MCP server (Hlobo-dev/tengu-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Tengu, and thousands of servers like it.
This server
Across the catalogue