Deterministic JSON repair for LLM agents. Strips prose preambles, fixes malformed control characters, repairs truncated structures, and validates against JSON Schema — no LLM calls, no retries. Stops session poisoning in long-running agents.
Scored across 4 tools
The three repair tools (repair_json, repair_string, sanitize_json_output) have heavily overlapping purposes. While repair_string has a more detailed description, an agent may struggle to choose between it, the generic repair_json, and sanitize_json_output, which also repairs control characters and removes prose. Only validate_json is clearly distinct.
The names mix patterns: repair_json and repair_string use the 'repair' verb with different objects, while validate_json and sanitize_json_output use other verbs. The object naming is also inconsistent (json, string, json_output). Overall the set is readable but lacks a uniform convention.
Four tools is a reasonable count for a JSON sanity server, fitting within the typical well-scoped range. However, the inclusion of three overlapping repair functions suggests the count could be trimmed without losing core functionality.
The server covers the full lifecycle for its stated purpose: validation (validate_json), repair (repair_json, repair_string), and sanitization (sanitize_json_output). It includes schema validation in repair_string, leaving no obvious gaps in the domain of ensuring JSON sanity.
Attempt to repair common JSON issues: trailing commas, single quotes, unquoted keys, Python/JS literals, truncated structures.
Inputs: json_string (required), api_key_id.
Deterministic repair engine. Given a raw LLM output that should contain JSON, this tool: (1) strips markdown code fences (```json), (2) regex-strips prose preambles/suffixes, (3) escapes unescaped control characters inside string values, (4) validates with json.loads — falling back to structural repairs and partial-recovery bracket closing when needed, and (5) optionally validates the repaired JSON against a JSON schema.
Inputs: raw_string (required), schema, api_key_id.
Use this tool before saving any JSON data to session history or state files to prevent JSONDecodeErrors and session poisoning. It removes prose preambles and repairs malformed control characters.
Inputs: raw_string (required), api_key_id.
Check whether a JSON string is valid. Returns parsed object on success.
Inputs: json_string (required), api_key_id.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Add one secure layer between your agents and this server.