Lordevo Shop (x402 website checks)

CSV/TSV to JSON with delimiter, header and type detection ($0.002/call)

csv_parse

Read-onlyIdempotent

$0.002 per call (x402, USDC on Base; free trial: add "trial": true or use try_free). [Data utilities] Parses CSV or TSV text into JSON rows (objects or arrays). Detects the delimiter (comma, semicolon, tab, pipe), the header row and quoting (RFC 4180: quoted commas, doubled quotes, newlines in quotes), infers column types and flags formula-injection cells (= + - @). Input: csv (POST for long text), optional delimiter, header, output, types, quote, max_rows. Limits: 1,000,000 characters, 50,000 rows, 500 columns. Offline.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "csv": "<csv>"
    },
    "name": "csv_parse"
  }
}

Input Schema

Name	Required	Description	Default
`csv`	Yes	CSV or TSV text, up to 1,000,000 characters (POST JSON {"csv": "..."} for long text)
`quote`	No	Quote character: double (default), single or none	double
`trial`	No	Optional. true = free if a trial call is left (3 per IP per UTC day), else the payment terms.
`types`	No	Infer column types and convert numbers and booleans (default yes); no keeps every cell as text	yes
`header`	No	Is the first row a header? auto (default, detected), yes or no	auto
`output`	No	Rows as objects keyed by column name (default) or as arrays	objects
`max_rows`	No	Rows returned, 1-5000 (default 1000); column stats still cover every parsed row	1000
`delimiter`	No	Field separator: auto (default, detected), comma, semicolon, tab or pipe	auto

Output Schema

Name	Required	Description
`rows`	No
`tool`	No
`cache`	No
`_trial`	No	Present when the call was a free trial call.
`header`	No
`output`	No
`columns`	No
`provider`	No
`warnings`	No
`delimiter`	No
`price_usd`	No
`row_count`	No
`truncated`	No
`column_count`	No
`formula_cells`	No
`rows_returned`	No
`delimiter_detected`	No
`header_detected_by`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedNov 5, 2026

changedInput schema / properties / trial / description

Previous value: -"Optional. true = answer free if a trial call is left (3 per IP per UTC day); otherwise you get the payment terms."New value: +"Optional. true = free if a trial call is left (3 per IP per UTC day), else the payment terms."

Changed2 schema fields changedNov 3, 2026

addedInput schema / properties / trial

Added value: +{
+  "description": "Optional. true = answer free if a trial call is left (3 per IP per UTC day); otherwise you get the payment terms.",
+  "type": "boolean"
+}

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "anyOf": [
+    {
+      "required": [
+        "tool",
+        "columns",
+        "rows",
+        "row_count"
+      ]
+    },
+    {
+      "properties": {
+        "accepts": {
+          "type": "array"
+        },
+        "error": {
+          "type": "string"
+        },
+        "resource": {
+          "type": "object"
+        },
+        "x402Version": {
+          "type": "integer"
+        }
+      },
+      "required": [
+        "x402Version",
+        "accepts"
+      ]
+    },
+    {
+      "properties": {
+        "charged": {
+          "type": "boolean"
+        },
+        "error": {
+          "type": "string"
+        },
+        "message": {
+          "type": "string"
+        }
+      },
+      "required": [
+        "error"
+      ]
+    }
+  ],
+  "properties": {
+    "_trial": {
+      "description": "Present when the call was a free trial call.",
+      "type": "object"
+    },
+    "cache": {
+      "type": "object"
+    },
+    "column_count": {
+      "type": "integer"
+    },
+    "columns": {
+      "items": {
+        "properties": {
+          "empty_count": {
+            "type": "integer"
+          },
+          "index": {
+            "type": "integer"
+          },
+          "name": {
+            "type": "string"
+          },
+          "type": {
+            "enum": [
+              "string",
+              "integer",
+              "number",
+              "boolean",
+              "date",
+              "datetime",
+              "empty"
+            ],
+            "type": "string"
+          }
+        },
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "delimiter": {
+      "enum": [
+        "comma",
+        "semicolon",
+        "tab",
+        "pipe"
+      ],
+      "type": "string"
+    },
+    "delimiter_detected": {
+      "type": "boolean"
+    },
+    "formula_cells": {
+      "type": "object"
+    },
+    "header": {
+      "type": "boolean"
+    },
+    "header_detected_by": {
+      "type": "string"
+    },
+    "output": {
+      "enum": [
+        "objects",
+        "arrays"
+      ],
+      "type": "string"
+    },
+    "price_usd": {
+      "type": "number"
+    },
+    "provider": {
+      "type": "string"
+    },
+    "row_count": {
+      "type": "integer"
+    },
+    "rows": {
+      "type": "array"
+    },
+    "rows_returned": {
+      "type": "integer"
+    },
+    "tool": {
+      "type": "string"
+    },
+    "truncated": {
+      "type": "boolean"
+    },
+    "warnings": {
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    }
+  },
+  "type": "object"
+}

AddedNov 2, 2026

TDQS

A4.3/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), and the description adds substantial context beyond them: hard limits of 1,000,000 characters, 50,000 rows and 500 columns; RFC 4180 quoting behavior; type inference; formula-injection flagging; and pricing with a free-trial path. These are exactly the operational constraints an agent needs before calling.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Pricing, category tag, purpose and limits are front-loaded in a dense but scannable sequence, with no filler sentences. The parameter enumeration repeats what the schema already lists and the '[Data utilities]' tag adds little, keeping it short of ideal.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For an 8-parameter tool with an output schema and full annotation coverage, the description supplies limits, detection heuristics, and payment mechanics. It omits error behavior (malformed CSV, exceeded limits) and any note on how truncation interacts with the returned stats beyond a parenthetical, which keeps it from a 5.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents every parameter, including enums and defaults. The description only enumerates the optional parameters ('delimiter, header, output, types, quote, max_rows') and adds the marginal note that column stats cover every parsed row even when max_rows truncates output. That is the baseline for high schema coverage, not more.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource: 'Parses CSV or TSV text into JSON rows (objects or arrays)', plus concrete detection behaviors (delimiter, header, quoting) and type inference. This clearly separates it from siblings such as feed_parse, text_extract and json_repair, which handle other input formats.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives clear context for use: raw CSVs, mentions POSTing long text, the `trial` flag and the `try_free` sibling as a payment alternative, and marks the tool 'Offline.' It does not explicitly say when to prefer feed_parse or text_extract instead, so the sibling routing is implied rather than stated.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Lordevo Shop (x402 website checks) tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?