Match extracted tender requirements against company capabilities and documents.
AI agents call match_company_profile to retrieve information from EPC Tender Screening MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a matching/comparison operation between tender requirements and company capabilities. It reads and analyzes existing data to produce a match result, with no side effects, data modification, or external operations. It is essentially a query/analysis tool that retrieves and compares information.
From the tool's definition Match extracted tender requirements against company capabilities and documents
Attacks that exploit this kind of access
Match extracted tender requirements against company capabilities and documents. It is categorised as a Read tool in the EPC Tender Screening MCP MCP Server, which means it retrieves data without modifying state.
Register the EPC Tender Screening MCP server in PolicyLayer and add a rule for match_company_profile: 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 EPC Tender Screening MCP. Nothing to install.
match_company_profile 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 match_company_profile 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 match_company_profile. 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.
match_company_profile is provided by the EPC Tender Screening MCP server (shiverion/epc-tender-screening-mcp-showcase). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →