Skip to content

Spatial India MCP server

com.spatialindia/spatial-indiaspatialindia.comstreamable-httpv1.0.0Scanned

District-level open data for India — Census, NFHS-5, NCRB, RBI and more, joined onto one geography.

6 tools: 2 change things and 4 only read.

Tools: 0 delete, 0 irreversible, 2 write, 4 read.
  • Reads private data · 0
  • Reads text others write · 0
  • Can send data out · 0
  • 2 findings

Tools listed without sign-in. Remote posture

With Anlyon

2 tools here change things. Govern them.

  • Anlyon lists the tools and adopts none.
  • Each tool you adopt gets approvals and receipts.
  • Your agent never holds the key.
Govern this server →

A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.

What the Spatial India MCP server can do

The Spatial India MCP server is published by spatialindia.com, a domain the MCP Registry verified. It has 6 tools. It can create or change data (2 tools: rank_districts and build_map_link), but cannot delete data. 4 tools only read.

None of its tools reads private data, brings in text other people write, or sends data out.

The fixed checks matched 2 findings (tool-shadowing and annotation-conflict). Each one comes with the text it matched.

Its remote endpoint lists its tools without sign-in.

Last scanned Nov 14, 2026, version 1.0.0.

Tools

Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.

6 tools

Changes things 2Claude Code: ask
  • rank_districtsUse for best/worst/highest/lowest questions over many districts — "worst 20 districts for child stunting in Uttar Pradesh".No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    Use for best/worst/highest/lowest questions over many districts — "worst 20 districts for child stunting in Uttar Pradesh". Check the indicator's `polarity` in the result before calling a tail "worst": for a higher-worse indicator the worst districts are `order: "desc"`, for higher-better they are `order: "asc"`. Districts the source never covered sort last in both directions and are never presented as an extreme.

    Annotations the server declares

    • title: Rank districts
    • readOnlyHint: true
    • openWorldHint: false
Only reads 4Show 4 read-only tools
  • compare_districtsUse when the question names two or more places and asks how they differ — "compare Pune and Nagpur on literacy and bank credit".No findings

    Why it is in this group

    • The name "compare_districts" says "compare": a word for reading.
    Description, as the server wrote it
    Use when the question names two or more places and asks how they differ — "compare Pune and Nagpur on literacy and bank credit". One call, not one get_district per district. Write an ambiguous name as "Bilaspur, Chhattisgarh".

    Annotations the server declares

    • title: Compare districts
    • readOnlyHint: true
    • openWorldHint: false
  • find_indicatorUse FIRST, before any other tool, whenever a question names a subject rather than an indicator id — "stunting", "land inequality", "bank credit".1 finding

    Why it is in this group

    • The name "find_indicator" says "find": a word for reading.

    Findings

    • Warn

      The description contains "any other tool", wording about other tools or servers.

      Matched text

      description: "Use FIRST, before any other tool, whenever a question names a subject ra..."

      What this check looks for
    Description, as the server wrote it
    Use FIRST, before any other tool, whenever a question names a subject rather than an indicator id — "stunting", "land inequality", "bank credit". Returns matching indicator ids with their unit, source, vintage, caveat and district coverage. Every other tool needs an id from here; ids are not guessable and inventing one fails.

    Annotations the server declares

    • title: Find an indicator
    • readOnlyHint: true
    • openWorldHint: false
  • get_districtUse when the question is about one named place — "tell me about Bilaspur", "what is Pune's literacy rate".No findings

    Why it is in this group

    • The name "get_district" says "get": a word for reading.
    Description, as the server wrote it
    Use when the question is about one named place — "tell me about Bilaspur", "what is Pune's literacy rate". Resolves an Indian district name, including common alternative spellings, to its objectid and returns its values. Four district names are shared by two states, so if the name is ambiguous this returns every match with its state and no data: ask the user which one, then call again with `state`.

    Annotations the server declares

    • title: Get one district
    • readOnlyHint: true
    • openWorldHint: false
  • get_methodologyUse whenever the answer will state a number to a user, and always when asked how a figure was produced, how old it is, or whether it can be trusted.No findings

    Why it is in this group

    • The name "get_methodology" says "get": a word for reading.
    Description, as the server wrote it
    Use whenever the answer will state a number to a user, and always when asked how a figure was produced, how old it is, or whether it can be trusted. Returns the source, vintage, definition, caveat, estimation method, licence attribution and the citation string for one indicator, or for the dataset as a whole when no indicator is given. Do not describe a number as measured or estimated without checking here — each district carries its own `estimated` flag.

    Annotations the server declares

    • title: Get methodology and citation
    • readOnlyHint: true
    • openWorldHint: false

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Exfil surface

Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.

No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data or untrusted-input or outbound.

Reads private data0
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write0
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out0
Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.

Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.

Remote posture

What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.

Tools listed without sign-in

Looked at Nov 20, 2026, 18:47 UTC, unchanged since Oct 22, 2026. No credentials were sent and no tool was called. What is looked at.

Reachable
yes
HTTP status of an anonymous initialize
200
tools/list served without credentials
yes
Tools that change things, listed without credentials
2
Protocol version
2025-06-18
WWW-Authenticate on 401
not observed
resource_metadata in WWW-Authenticate
not observed
RFC 9728 protected resource metadata
not observed
Authorization servers
not observed
Legacy HTTP+SSE transport
no
Dynamic client registration
not observed
Client ID metadata documents
not observed
  • WarnThe whole server

    The endpoint served tools/list without credentials, and the list has 2 tools that change things (2 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://api.spatialindia.com/mcp: tools/list returned 6 tools to an anonymous client, including rank_districts (write), build_map_link (write)

    What this check looks for

Findings

Matches of fixed checks, with the text they matched.

2 warn
  • The description contains "any other tool", wording about other tools or servers.

    Matched text

    description: "Use FIRST, before any other tool, whenever a question names a subject ra..."

    What this check looks for
  • The server marks "build_map_link" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

    Matched text

    annotations: {"readOnlyHint":true,"openWorldHint":false}; The name "build_map_link" says "link": a word for a change.

    What this check looks for

History

Changes to its tool definitions and to its remote endpoint, newest first.

No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.

Install

Pinned to version 1.0.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http spatial-india https://api.spatialindia.com/mcp
claude mcp add --transport http spatial-india https://api.spatialindia.com/mcp

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__spatial-india__find_indicator",
      "mcp__spatial-india__get_district",
      "mcp__spatial-india__compare_districts",
      "mcp__spatial-india__get_methodology"
    ],
    "ask": [
      "mcp__spatial-india__rank_districts",
      "mcp__spatial-india__build_map_link"
    ],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as spatial-india. Review it before you use it.

Pin

Keep the decision: fail CI when the tools change, follow every change, or show a badge.

Pin in CI

Fail a build when the tools you reviewed are not the tools the server serves today.

curl -s "https://radar.anlyon.com/api/v1/servers/com.spatialindia/spatial-india/verify?hash=d4f398c6f0a7fada40cb92065a509b632af2bf4be30f95294b529b5db9374e3b" | jq -e '.changed == false'

Pinned hash d4f398c6f0a7, from Nov 14, 2026, 10:17 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://radar.anlyon.com/servers/com.spatialindia/spatial-india/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Badge

Anlyon Radar badge for com.spatialindia/spatial-india
[![Anlyon Radar](https://radar.anlyon.com/badge/com.spatialindia/spatial-india.svg)](https://radar.anlyon.com/servers/com.spatialindia/spatial-india)

Source: MCP Registry. Synced Oct 21, 2026, 18:05 UTC.

Spatial India MCP server: questions and answers

Answered from the scan above, not from the publisher's description.

Is the Spatial India MCP server safe?

No scan can promise that. What its definitions show: 6 tools, 2 of which can change, send or delete something, and 2 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.

Can the Spatial India MCP server delete data?

No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.

Can the Spatial India MCP server do things that cannot be undone?

No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.

What tools does the Spatial India MCP server have?

6 tools: 2 write, 4 read. rank_districts, build_map_link, find_indicator, get_district, compare_districts and get_methodology.

Does the Spatial India MCP server need sign-in or OAuth?

Its remote endpoint listed its tools to an anonymous client, without sign-in.

Does the Spatial India MCP server send data to outside services?

None of its tools sends, posts or publishes, or takes a recipient, channel or URL.

Has the Spatial India MCP server changed its tools?

Not since Anlyon Radar started tracking it. Last scanned Nov 14, 2026.