This record as markdown: /tools/io-github-portel-dev-ncp/get-pipeline.md
What get_pipeline does on Ncp
AI agents call get_pipeline to retrieve information from Ncp without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why get_pipeline is rated Low
This tool retrieves or queries CircleCI pipeline information. It performs a read-only operation to fetch metadata or status details about an existing pipeline. There is no indication that it modifies data, executes the pipeline, deletes resources, or commits financial transactions.
From the tool's definition Tool name is 'get_pipeline' and description states 'Get CircleCI pipeline details' — the verb 'Get' indicates data retrieval without modification or execution of the pipeline itself.
Attacks that exploit this kind of access
The rule that runs get_pipeline safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Ncp, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For get_pipeline, this is the rule to start with:
get_pipeline is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Ncp, apply this rule, and every get_pipeline call is checked against it from then on.
Questions about get_pipeline
Get CircleCI pipeline details. It is categorised as a Read tool in the Ncp MCP Server, which means it retrieves data without modifying state.
Register the Ncp MCP server in PolicyLayer and add a rule for get_pipeline: 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 Ncp. Nothing to install.
get_pipeline is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_pipeline 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 get_pipeline. 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.
get_pipeline is provided by the Ncp MCP server (@portel/ncp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Ncp, and thousands of servers like it.
This server
Across the catalogue