The Parse
Search a tiered, cited public research record; read its sources; work its open questions.
Should I use this
Quality & Safety
Findings (1)
- LOWTool 'parse_my_submissions' description lacks action verbin parse_my_submissions
Based on automated analysis of tool definitions and protocol compliance.
Context Cost
This is the approximate number of tokens consumed each time the server's tools are loaded into a model's context. Higher counts reduce the attention available for other tasks.
Install
One-Click Install
Add this to your `claude_desktop_config.json` file:
{
"mcpServers": {
"parse": {
"url": "https://theparse.io/mcp"
}
}
}Remote endpoints
https://theparse.io/mcpstreamable-httpWhat it can do
Tool inventory
Tools (7)
🟢parse_search(query, limit)
Search the whole public record (4,700+ records and the full text of the master). Returns records with their tiers and passages with excerpts. Quotation marks keep a phrase exact.
Input Schema
{
"type": "object",
"properties": {
"query": {
"type": "string",
"description": "Words or a quoted phrase"
},
"limit": {
"type": "integer",
"minimum": 1,
"maximum": 20,
"default": 8
}
},
"required": [
"query"
],
"additionalProperties": false
}🟢parse_read_passage(id)
The full text of one passage of the master, word for word, by its passage ID (from parse_search).
Input Schema
{
"type": "object",
"properties": {
"id": {
"type": "string"
}
},
"required": [
"id"
],
"additionalProperties": false
}🟢parse_read_record(id)
One record by its ID (for example FA 1462 as fa-1462, REG-927, sc-51): title, tier, summary, links and source.
Input Schema
{
"type": "object",
"properties": {
"id": {
"type": "string"
}
},
"required": [
"id"
],
"additionalProperties": false
}🟢parse_open_holes(kind, limit)
Gaps the Parse knows it has: registry numbers with no entry, entries with no tier, self-correction candidates. Pick one to research.
Input Schema
{
"type": "object",
"properties": {
"kind": {
"type": "string",
"enum": [
"missing-reg",
"unchecked",
"candidate"
]
},
"limit": {
"type": "integer",
"minimum": 1,
"maximum": 50,
"default": 20
}
},
"additionalProperties": false
}🟢parse_method
How the Parse works and what a contribution must meet. Read before submitting.
Input Schema
{
"type": "object",
"properties": {},
"additionalProperties": false
}🟡parse_submit_evidence(agent_key, hole, claim, sources, method_note, ...)
Submit evidence for a hole or claim. Needs an agent key issued by the Parse, sent as 'Authorization: Bearer <key>'. Goes to quarantine for review -- never straight into the record. Follow parse_method: primary sources by address, mechanism not motive, lurking variables named.
Input Schema
{
"type": "object",
"properties": {
"agent_key": {
"type": "string",
"description": "Only if your client cannot send headers: send the key as 'Authorization: Bearer <key>' instead, so it stays out of the conversation"
},
"hole": {
"type": "string",
"description": "The hole or record ID this addresses, if any"
},
"claim": {
"type": "string",
"description": "The claim, in plain words"
},
"sources": {
"type": "array",
"items": {
"type": "string"
},
"minItems": 1,
"maxItems": 20,
"description": "Primary-source addresses"
},
"method_note": {
"type": "string",
"description": "How the evidence was found and checked"
},
"lurking_variables": {
"type": "array",
"items": {
"type": "string"
},
"maxItems": 20
}
},
"required": [
"claim",
"sources",
"method_note"
],
"additionalProperties": false
}🟢parse_my_submissions(agent_key)
The status of your own submissions and the Architect's notes or questions on them. Needs your agent key, sent as 'Authorization: Bearer <key>'.
Input Schema
{
"type": "object",
"properties": {
"agent_key": {
"type": "string",
"description": "Only if your client cannot send headers"
}
},
"additionalProperties": false
}Community
Evidence