Skip to main content
Glama
streamparse-mcp

streamparse-mcp

by MukundaKatta

streamparse-mcp

npm tests mcp

An MCP server that gives AI assistants the ability to parse partial / messy / truncated JSON.

Built on top of @mukundakatta/streamparse. Works with Claude Desktop, Cursor, Cline, Windsurf, Zed, and any other MCP client.

Tools exposed

parse_partial_json

Recover a JSON value from a possibly-truncated string. Always returns a valid value with synthetic closure of any open strings, arrays, or objects.

{
  "text": "{\"type\":\"tool_use\",\"name\":\"edit_file\",\"input\":{\"path\":\"a/b.ts\",\"cont"
}

→

{
  "value": {
    "type": "tool_use",
    "name": "edit_file",
    "input": { "path": "a/b.ts", "cont": null }
  },
  "complete": false,
  "path": ["input", "cont"],
  "bytes_consumed": 67,
  "confidence": 0.65
}

extract_json_from_text

Strip prose, ```json fences, and comments around a JSON value embedded in LLM output. Returns the first parseable value.

Sure, here you go:
```json
{ "answer": 42 }

Let me know!


→ `{ "answer": 42 }`

### `validate_json`

Strict-mode RFC 8259 validator. Returns `ok=true` and the parsed value on
success, or `ok=false` with a precise byte position and error message on
failure.

## Install

### Claude Desktop

Add to `claude_desktop_config.json`:

```json
{
  "mcpServers": {
    "streamparse": {
      "command": "npx",
      "args": ["-y", "@mukundakatta/streamparse-mcp"]
    }
  }
}

Cursor / Cline / Windsurf / Zed

Same shape, in the appropriate mcp.json for your client. Most clients auto-discover via npx -y @mukundakatta/streamparse-mcp.

Local install

npm install -g @mukundakatta/streamparse-mcp
mcp-streamparse        # listens on stdio

Related MCP server: json-promptor-mcp

Why this matters

When an LLM is mid-tool-call and you need the assistant to reason about the half-formed JSON it just wrote, no other tool gives a usable answer. Standard JSON.parse throws. Regex extraction misses nested structure. This MCP server gives Claude (or whichever model is driving) a real handle on partial JSON, right where it lives.

License

MIT.

Available Tools

3 tools
extract_json_from_textA

Extract and parse a JSON value embedded in messy LLM output. Strips ```json fences, leading/trailing prose, code comments, and tolerates other LLM-isms. Returns the first parseable value and where in the text it started.

Inputs: text (required).

parse_partial_jsonA

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 any open strings, arrays, or objects. Reports whether the input represented a complete top-level value, plus the cursor path where parsing stopped.

Inputs: text (required), lenient.

validate_jsonA

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 position and human-readable message.

Inputs: text (required).

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A4.4/5.0

    Scored across 3 tools

    Disambiguation5/5

    Each tool targets a distinct JSON scenario: partial/truncated input, embedded in LLM text, and strict validation. No overlap in purpose.

    Naming Consistency5/5

    All tools follow a consistent verb_noun pattern (parse_partial_json, extract_json_from_text, validate_json), making the set predictable.

    Tool Count5/5

    Three tools is well-scoped for a focused JSON parsing and validation server—each tool serves a clear need without excess or deficiency.

    Completeness5/5

    The surface covers the key JSON handling tasks: parsing partial streams, extracting from messy text, and strict validation. No obvious gaps given the domain.

    Maintenance

    ActivityInactive
    ResponsivenessOutdated data

    Related MCP Connectors

    Related MCP Servers