get_source_capabilities
AI agents call get_source_capabilities to retrieve information from BigContext MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool name pattern indicates a getter/read operation that retrieves capability information about a source, likely returning static metadata or configuration data. No indication of modification, deletion, execution, or financial transaction. The tool belongs to a document analysis platform focused on reading and segmenting content.
From the tool's definition Tool name 'get_source_capabilities' suggests querying or retrieving capability information from a source, consistent with introspection or metadata retrieval. No description provided to confirm behavior.
Attacks that exploit this kind of access
get_source_capabilities. It is categorised as a Read tool in the BigContext MCP MCP Server, which means it retrieves data without modifying state.
Register the BigContext MCP server in PolicyLayer and add a rule for get_source_capabilities: 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 BigContext MCP. Nothing to install.
get_source_capabilities 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_source_capabilities 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_source_capabilities. 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_source_capabilities is provided by the BigContext MCP server (rixmerz/bigcontext_mcp). 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 →