New Your team’s decisions, in one playbook every coding agent works from. Never answer your agent twice

link_proposition

Say that a node ASSUMES this proposition: a goal (or strategy), a decision, an idea or an indicator rests on this claim. An edge with a reason; the target does not change. When the proposition is falsified, the linked decision and strategy are marked on read. Linking a pair that is already linked...

SERVERAdrata SOURCE@adrata/adrata-mcp
Low RISK CLASS
Category Read
Parameters 00 required
Recommended Allowedsee the rule below
Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/adrata-adrata-mcp/link-proposition.md

What link_proposition does on Adrata

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

Why link_proposition is rated Low

Even though link_proposition only reads data, uncontrolled read access leaks sensitive information and racks up API costs: an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.

Questions about link_proposition

What does the link_proposition tool do? +

Say that a node ASSUMES this proposition: a goal (or strategy), a decision, an idea or an indicator rests on this claim. An edge with a reason; the target does not change. When the proposition is falsified, the linked decision and strategy are marked on read. Linking a pair that is already linked replaces the reason (an upsert on the pair). The reason is recorded on the link and doubles as the audit reason.${GOVERNED_NOTE}. It is categorised as a Read tool in the Adrata MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on link_proposition? +

Register the Adrata MCP server in PolicyLayer and add a rule for link_proposition: 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 Adrata. Nothing to install.

What risk level is link_proposition? +

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

Can I rate-limit link_proposition? +

Yes. Add a rate_limit block to the link_proposition 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 link_proposition completely? +

Set action: deny in the PolicyLayer policy for link_proposition. 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 link_proposition? +

link_proposition is provided by the Adrata MCP server (@adrata/adrata-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

More on Adrata, and thousands of servers like it.

Across the catalogue

// THE MCP REGISTRY

PolicyLayer tracks 44,603 MCP servers and 515,000+ tools.

Every server has a live record: who publishes it, whether it answers without auth, its risk grade, every tool classified, the recommended policy. This page is one line of Adrata's. Pull the full record:

Teams ship this data inside their own products. See what a licence covers →

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.