hopcroft_karp
Find maximum matching in a bipartite graph using the Hopcroft-Karp algorithm in O(E * sqrt(V)).
This record as markdown: /tools/io-github-malamutemayhem-unclick-mcp-server/hopcroft-karp.md
What hopcroft_karp does on UnClick
AI agents invoke hopcroft_karp to trigger actions in UnClick. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call: builds kicked off, notifications sent, workflows started.
| Parameter | Type | Required | Description |
|---|---|---|---|
edges | array | Yes | Edges as [left_vertex, right_vertex] pairs |
left_size | number | Yes | Number of vertices on the left side |
right_size | number | Yes | Number of vertices on the right side |
Parameters from the server's own tool schema.
Why hopcroft_karp is rated High
This tool executes a graph algorithm (Hopcroft-Karp) on provided input data to compute a maximum bipartite matching. It performs a computation/execution rather than reading stored data or writing/modifying any data. The blast radius is low as it is a pure algorithmic computation with no side effects on external systems or data stores.
From the tool's definition "Find maximum matching in a bipartite graph using the Hopcroft-Karp algorithm" — runs a graph algorithm computation
Attacks that exploit this kind of access
The rule that runs hopcroft_karp safely
PolicyLayer is an MCP gateway: it sits between your AI agents and UnClick, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For hopcroft_karp, this is the rule to start with:
hopcroft_karp stays usable, but rate-capped: a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect UnClick, apply this rule, and every hopcroft_karp call is checked against it from then on.
Questions about hopcroft_karp
Find maximum matching in a bipartite graph using the Hopcroft-Karp algorithm in O(E * sqrt(V)). It is categorised as a Execute tool in the UnClick MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
hopcroft_karp accepts 3 parameters: edges, left_size, right_size. Required: edges, left_size, right_size. The full parameter table on this page comes from the server's own tool schema.
Register the UnClick MCP server in PolicyLayer and add a rule for hopcroft_karp: 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 UnClick. Nothing to install.
hopcroft_karp is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the hopcroft_karp 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 hopcroft_karp. 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.
hopcroft_karp is provided by the UnClick MCP server (@unclick/mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on UnClick, and thousands of servers like it.
Across the catalogue