// MCP TOOL REFERENCE

STREAMPARSE TOOLS

3 tools from the Streamparse MCP Server, categorised by risk level.

READ TOOLS

extract_json_from_text Extract and parse a JSON value embedded in messy LLM output. Strips ```json fences, leading/trailing prose, code comments, and tolerates other LLM-... validate_json Strict-mode RFC 8259 validator. Returns ok=true and the parsed value if the input is valid JSON; otherwise returns ok=false with a precise byte pos...

EXECUTE TOOLS

parse_partial_json Parse a JSON string that may be truncated mid-stream (e.g. a partial LLM tool call). Always returns a valid JSON value with synthetic closure of an...

// FAQ

How many tools does the Streamparse MCP server have? +

The Streamparse MCP server exposes 3 tools across 2 categories: Read, Execute.

How do I enforce policies on Streamparse tools? +

Use Intercept, the open-source MCP proxy. Write YAML rules for each tool — rate limits, argument validation, or deny rules — then run Intercept in front of the Streamparse server.

What risk categories do Streamparse tools fall into? +

Streamparse tools are categorised as Read (2), Execute (1). Each category has a recommended default policy.

Let agents act without letting them run wild.

Deterministic policy on every MCP tool call. Per-identity grants. Full audit log.

GET STARTED →