compute_column
Add a column computed from arithmetic over an uploaded file's numeric columns, then map it. Pass file key, expression and result column, e.g. {"file key": "...", "expression": "(revenue - cost) / population", "result column": "profit per capita"}. Operators: + - / % and parentheses, or a single comparison ( = <= ==) between two operands. Column names are matched case-insensitively and may contain spaces; quote a name that looks like a number with backticks, e.g. 2023 - 2020 . A row whose referenced cells are blank or a missing-data marker (-, NA, N/A), or that divides by zero, gets an empty va
Показать схему аргументов
{
"type": "object",
"required": [
"file_key",
"expression"
],
"properties": {
"sheet": {
"type": "string"
},
"file_key": {
"type": "string"
},
"expression": {
"type": "string",
"description": "arithmetic over column names, e.g. (revenue - cost) / population; operators + - * / % and parentheses, or one comparison > < >= <= =="
},
"result_column": {
"type": "string"
}
},
"additionalProperties": false
}
geocode
Geocode addresses from an uploaded CSV or XLSX file into latitude/longitude. Pass a file key from upload file. Single place, no file: pass only address (e.g. {"address": "India Gate, New Delhi"}). The reply carries latitude, longitude, address, pincode, city, district, state and landmark. status=not found means no match; tell the user rather than answering yourself. Column selection: if you know it, pass address column (or address columns for several). Otherwise the server asks the geo-match service to detect it. When the answer is not unambiguous — several address columns, a weak match, or on
Показать схему аргументов
{
"type": "object",
"properties": {
"sheet": {
"type": "string"
},
"job_id": {
"type": "string"
},
"address": {
"type": "string"
},
"file_key": {
"type": "string"
},
"force_new": {
"type": "boolean"
},
"address_column": {
"type": "string"
},
"address_columns": {
"type": [
"null",
"array"
],
"items": {
"type": "string"
}
},
"compose_columns": {
"type": [
"null",
"array"
],
"items": {
"type": "string"
}
}
},
"additionalProperties": false
}
get_capabilities
Return the server's capability matrix: supported map types, geo types, output formats, classification methods, and the list of tools available in this process (which varies by configuration). Call this first to discover what the server can do.
Показать схему аргументов
{
"type": "object",
"additionalProperties": false
}
pincode_lookup
Look up Indian pincodes: city, district and state. One pincode, no file: {"pincode": "560019"} also returns the post offices it covers with their coordinates. status=not found means the pincode does not exist; tell the user rather than answering yourself. A file (including a local CSV the user names): upload it with upload file first, then pass file key (and pincode column if you know it). Do not look the rows up one by one or write the result file yourself — this tool writes it. Every row gains city, district, state and pincode status columns; the file is written back over file key as a new v
Показать схему аргументов
{
"type": "object",
"properties": {
"sheet": {
"type": "string"
},
"job_id": {
"type": "string"
},
"pincode": {
"description": "one 6-digit Indian pincode, e.g. \"560019\" (a number is accepted too)"
},
"file_key": {
"type": "string"
},
"force_new": {
"type": "boolean"
},
"pincode_column": {
"type": "string"
}
},
"additionalProperties": false
}
question_to_map
Render a geographic map from your data. Call upload file first to ingest a CSV/XLSX file, then pass the returned file key: {"question": "show total by pincode", "file key": "mcp-uploads/ /2026/01/15/ .csv"}. The file key is reusable — for additional questions on the same file, pass the same file key again without re-uploading. Alternatively, pass rows directly as 'data' (e.g. from the upload file preview): {"question": "show total by pincode", "data": [ ]} geo column and value column are preferred if easily identifiable from the column names, but not required — the server auto-detects them usi
Показать схему аргументов
{
"type": "object",
"required": [
"question"
],
"properties": {
"data": {
"type": [
"null",
"array"
],
"items": {
"type": "object",
"additionalProperties": true
}
},
"sheet": {
"type": "string"
},
"style": {
"type": "object",
"additionalProperties": true
},
"table": {
"type": "string"
},
"title": {
"type": "string"
},
"file_key": {
"type": "string"
},
"map_type": {
"type": "string"
},
"question": {
"type": "string"
},
"subtitle": {
"type": "string"
},
"geo_level": {
"type": "string"
},
"geo_column": {
"type": "string"
},
"state_hint": {
"type": [
"null",
"array"
],
"items": {
"type": "string"
}
},
"enrich_with": {
"type": [
"null",
"object"
],
"required": [
"table",
"columns"
],
"properties": {
"table": {
"type": "string"
},
"columns": {
"type": [
"null",
"array"
],
"items": {
"type": "string"
}
},
"join_on": {
"type": "string"
}
},
"additionalProperties": false
},
"detected_geo": {
"type": [
"null",
"object"
],
"required": [
"column",
"geo_type",
"confidence",
"matched_count",
"total_count"
],
"properties": {
"column": {
"type": "string"
},
"parent": {
"type": "string"
},
"geo_type": {
"type": "string"
},
"confidence": {
"type": "number"
},
"total_count": {
"type": "integer"
},
"matched_count": {
"type": "integer"
}
},
"additionalProperties": false
},
"legend_title": {
"type": "string"
},
"value_column": {
"type": "string"
},
"output_format": {
"type": "string"
},
"render_params": {
"type": "object",
"additionalProperties": true
}
},
"additionalProperties": false
}
reverse_geocode
Turn latitude/longitude coordinates in an uploaded CSV or XLSX into addresses. Pass a file key from upload file. Single point, no file: pass only latitude and longitude in decimal degrees (e.g. {"latitude": 28.6129, "longitude": 77.2295}). The reply carries address, pincode, city, district, state and landmark. status=not found means no match; tell the user rather than answering yourself. Column selection: pass latitude column and longitude column, or latlong column for a single combined column, or coordinate pairs for several sets. Otherwise the server detects them. When the answer is not unam
Показать схему аргументов
{
"type": "object",
"properties": {
"sheet": {
"type": "string"
},
"job_id": {
"type": "string"
},
"file_key": {
"type": "string"
},
"latitude": {
"description": "one point's latitude in decimal degrees, e.g. 28.6129 (a string is accepted too)"
},
"force_new": {
"type": "boolean"
},
"longitude": {
"description": "one point's longitude in decimal degrees, e.g. 77.2295 (a string is accepted too)"
},
"latlong_column": {
"type": "string"
},
"latitude_column": {
"type": "string"
},
"coordinate_pairs": {
"type": [
"null",
"array"
],
"items": {
"type": "object",
"properties": {
"latlong_column": {
"type": "string"
},
"latitude_column": {
"type": "string"
},
"longitude_column": {
"type": "string"
}
},
"additionalProperties": false
}
},
"longitude_column": {
"type": "string"
},
"accept_low_precision": {
"type": "boolean"
}
},
"additionalProperties": false
}
territory_mapping
Run the territory-management pipeline on a branch file uploaded via upload file. Hybrid async with three modes: pass file key to START a job (returns a job id immediately); pass only job id on subsequent calls to POLL progress; pass job id AND catchment type together to RESUME a job that paused for clarification. The pipeline validates that all branches are in one state, computes each branch's isochrone at catchment distance km, finds villages (catchment type='village') or pincodes (catchment type='pincode') that overlap the isochrone by ≥50%. A village/pincode inside several catchments is kep
Показать схему аргументов
{
"type": "object",
"properties": {
"job_id": {
"type": "string"
},
"file_key": {
"type": "string"
},
"map_title": {
"type": "string"
},
"render_map": {
"type": [
"null",
"boolean"
]
},
"style_request": {
"type": "string"
},
"catchment_type": {
"type": "string"
},
"catchment_distance_km": {
"type": "number"
}
},
"additionalProperties": false
}
upload_file
Upload a CSV or XLSX file for server-side ingestion under policy (auth, size cap, malware scan, injected-intent scan) and receive a file key. This is the first step for ANY tool that works on the user's file: question to map, geocode, reverse geocode, pincode lookup and compute column all take the returned file key. When the user names a local CSV/XLSX and wants results added to it (pincodes, cities, coordinates, a computed column), upload it here rather than reading it yourself. Step 1: Call upload file with file name, file size, and question. The response contains a signed upload url and a c
Показать схему аргументов
{
"type": "object",
"required": [
"file_name",
"file_size"
],
"properties": {
"sheet": {
"type": "string"
},
"file_key": {
"type": "string"
},
"question": {
"type": "string"
},
"file_name": {
"type": "string"
},
"file_size": {
"type": "integer"
}
},
"additionalProperties": false
}