What can you do with this server?

The PlanWire MCP server provides tools to search, explore, and retrieve UK planning application data: * Search planning applications (search_planning_applications): Search by keyword, council ID, postcode, application status (Pending/Approved/Refused/Withdrawn), type (e.g. Householder, Full, Listed Building), or date range — with pagination and result limits. * Find nearby planning applications (nearby_planning_applications): Locate applications within a specified radius of a given latitude/longitude (WGS84) coordinate. * Get a specific planning application (get_planning_application): Fetch full details of a single application by its unique PlanWire ID. * List covered councils (list_councils): Retrieve all UK local planning authorities (councils) covered by PlanWire, along with their IDs for use in searches.

How do I use planwire-mcp?

1. Click on "Install Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@planwire-mcp Search for recent planning applications in Camden" That's it! The server will respond to your query, and you can continue using it as needed. Here is a step-by-step guide with screenshots.

planwire-mcp

by beshogun

Overview Schema Related Servers Score Discussions

JavaScript

Remote

PlanWire MCP Server

Use UK planning application data inside Claude, Cursor, and any MCP client.

PlanWire exposes fresh, normalised UK planning application data through a public API. This MCP server wraps that API as agent tools so an assistant can search applications, inspect a specific record, look near a location, and list supported councils without you writing API calls by hand.

Get a free sandbox API key at https://planwire.io/?utm_source=npm&utm_medium=mcp_readme&utm_campaign=mcp.

What MCP Is

Model Context Protocol (MCP) is a standard way for AI tools to call external services. You run this package locally through npx; it talks to PlanWire using your own API key and returns structured planning data to the MCP client.

This server uses stdio transport. It does not store credentials or run a hosted proxy.

Related MCP server: UK Property Intelligence

Install

You need Node.js 18+ and a PlanWire API key.

npx -y planwire-mcp

The server expects PLANWIRE_API_KEY in the environment. Optional: set PLANWIRE_API_BASE to override the default https://api.planwire.io.

Claude Desktop

Add this to claude_desktop_config.json:

{
  "mcpServers": {
    "planwire": {
      "command": "npx",
      "args": ["-y", "planwire-mcp"],
      "env": {
        "PLANWIRE_API_KEY": "your_planwire_key_here"
      }
    }
  }
}

Restart Claude Desktop after saving the config.

Claude Code

Add this to your project .mcp.json:

{
  "mcpServers": {
    "planwire": {
      "command": "npx",
      "args": ["-y", "planwire-mcp"],
      "env": {
        "PLANWIRE_API_KEY": "your_planwire_key_here"
      }
    }
  }
}

Cursor

Add the same server command in Cursor's MCP settings:

{
  "mcpServers": {
    "planwire": {
      "command": "npx",
      "args": ["-y", "planwire-mcp"],
      "env": {
        "PLANWIRE_API_KEY": "your_planwire_key_here"
      }
    }
  }
}

Tools

Tool	What it does
`search_planning_applications`	Search by keyword, council, postcode, status, type, or date range.
`nearby_planning_applications`	Find applications near a latitude/longitude point.
`get_planning_application`	Fetch one application by PlanWire application id.
`list_councils`	List covered councils and their IDs.

Example Prompts

"Search PlanWire for recent planning applications in Camden."
"Find refused householder extensions in OX1 from the last year."
"What planning applications are within 1km of 51.5074, -0.1278?"
"List the councils PlanWire covers."
"Find planning applications mentioning HMOs in Manchester."

Limits And Pricing

Free sandbox keys are suitable for testing and are capped on daily calls and result size. Paid plans increase limits for production use.

Pricing: https://planwire.io/?utm_source=npm&utm_medium=mcp_readme&utm_campaign=mcp#pricing

Troubleshooting

If the tool says PLANWIRE_API_KEY is not set, add your key to the MCP client config and restart the client.

If PlanWire returns 401, check that the key is correct and active.

If PlanWire returns 429, the key has reached its rate limit. Use fewer calls or upgrade at https://planwire.io/?utm_source=npm&utm_medium=mcp_readme&utm_campaign=mcp#pricing.

Development

npm install
npm run build
npm start

MIT licensed. Built by PlanWire: https://planwire.io/?utm_source=npm&utm_medium=mcp_readme&utm_campaign=mcp

Available Tools

4 tools

get_planning_applicationA

Fetch a single planning application by its PlanWire id.

ParametersJSON Schema

Name	Required	Description	Default
`id`	Yes	PlanWire application id.

TDQS

A3.7/5.0

Behavior2/5

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

No annotations are provided, so the description carries the full burden. It only states the basic action without disclosing any behavioral traits such as error handling (e.g., 404 if id not found), authentication requirements, rate limits, or idempotency. The description is too minimal for a tool with no annotations.

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

Conciseness5/5

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

The description is a single sentence of 10 words, containing exactly the needed information with no redundancy. It is front-loaded and efficient.

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

Completeness5/5

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

For a simple fetch-by-id tool with a single parameter, the description is complete. It specifies what the tool does and the required identifier. The absence of an output schema is acceptable as the return value (a planning application) is implied by the action. Sibling tools cover different use cases.

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 coverage is 100% (one parameter with description in schema). The description adds no additional meaning beyond the schema; it merely restates the parameter's purpose. Baseline of 3 is appropriate since the schema already provides sufficient definition.

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?

The description clearly states the action ('fetch'), the resource ('a single planning application'), and the identifier ('by its PlanWire id'). This distinguishes it from sibling tools that list, search, or find nearby applications.

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

Usage Guidelines3/5

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

The description implies usage when a specific PlanWire id is known, but it provides no explicit guidance on when to use this tool versus alternatives like search_planning_applications or list_councils. No exclusions or prerequisites are mentioned.

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

list_councilsA

List the UK councils (local planning authorities) PlanWire covers, with their IDs for use in searches.

ParametersJSON Schema

Name	Required	Description	Default
No parameters

TDQS

A4.2/5.0

Behavior3/5

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

No annotations are provided, so the description carries the full burden. It discloses the basic function (listing councils with IDs) but omits details like data freshness, sorting, pagination, or whether it's read-only. For a simple list tool, this is adequate but not thorough.

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

Conciseness5/5

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

A single sentence that is extremely concise and front-loaded, containing no wasted words.

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?

Given the tool's simplicity (no parameters, no output schema), the description covers the essential purpose and use case. It could be slightly improved by specifying the return format (e.g., list of objects), but overall it is complete enough.

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

Parameters4/5

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

There are zero parameters, and the schema coverage is 100% (empty object). The description adds no parameter details, but with 0 parameters the baseline is 4.

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?

The description clearly states the action ('list'), the subject ('UK councils (local planning authorities)'), the scope ('PlanWire covers'), and the purpose ('with their IDs for use in searches'). It effectively distinguishes from sibling tools like 'get_planning_application' which focus on applications.

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?

The phrase 'for use in searches' implies the IDs are meant for tools like 'search_planning_applications', providing usage context. However, it does not explicitly state when not to use this tool or mention alternative approaches.

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

nearby_planning_applicationsA

Find planning applications within a radius of a point (latitude/longitude). Use for 'what's been applied for near this location'.

ParametersJSON Schema

Name	Required	Description
`lat`	Yes	Latitude (WGS84).
`lng`	Yes	Longitude (WGS84).
`limit`	No	Max results (paid keys up to 100; free keys 10).
`radius_km`	No	Radius in kilometres (paid plans allow larger radii).

TDQS

A3.6/5.0

Behavior2/5

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

No annotations are provided, so the description must fully disclose behavior. It only says 'find applications within a radius' but does not mention if results are sorted, limited to active applications, paginated, or any rate limits. There is no contradiction but significant gaps.

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

Conciseness5/5

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

The description is extremely concise with two sentences, front-loading the core action. There is no redundant information.

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

Completeness2/5

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

Given 4 parameters and no output schema or annotations, the description is incomplete. It does not mention output format, pagination, or default values, leaving an agent with insufficient information for robust invocation.

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 baseline is 3. The description adds no additional parameter semantics beyond what is in the schema (e.g., default values for limit or radius_km are not clarified). It minimally meets expectations.

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?

The description clearly states the tool finds planning applications within a radius of a given point, using 'what's been applied for near this location' as a usage example. This distinguishes it from siblings like 'get_planning_application' (single app) and 'search_planning_applications' (likely text-based).

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?

The description provides a usage context ('what's been applied for near this location') and implicitly recommends this tool for proximity queries. However, it does not explicitly state when not to use it or compare with siblings like 'search_planning_applications' for text searches.

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

search_planning_applicationsA

Search UK planning applications by keyword, council, postcode, status, type, or date range. Returns matching applications with address, description, reference, status, and dates. Use for questions like 'recent planning applications in Camden' or 'refused extensions in OX1'.

ParametersJSON Schema

Name	Required	Description
`q`	No	Full-text search across address, description, and reference.
`page`	No	Page number (default 1).
`type`	No	Application type, e.g. 'Householder', 'Full', 'Listed Building'.
`limit`	No	Results per page (paid keys up to 100; free keys 10).
`status`	No	Filter by decision status.
`council`	No	Council ID, e.g. 'camden', 'oxford'.
`date_to`	No	Latest application date, YYYY-MM-DD.
`postcode`	No	Postcode or postcode prefix, e.g. 'OX1' or 'SW1A 1AA'.
`date_from`	No	Earliest application date, YYYY-MM-DD.

TDQS

A3.5/5.0

Behavior2/5

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

No annotations are provided, placing the full burden on the description. It mentions the returned fields but fails to disclose pagination behavior, rate limits, authentication needs, or error handling. This is insufficient for a tool with 9 parameters.

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

Conciseness5/5

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

Extremely concise: two sentences that front-load the purpose and include examples. No wasted words or redundant information. Ideal length for a search tool.

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

Completeness3/5

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

Given the tool's complexity (9 parameters, no output schema, no annotations), the description is adequate but not fully complete. It lists return fields and gives examples but omits details like pagination, optionality of all parameters, and free vs paid tier limit (which is in schema but not description). Could be more comprehensive.

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 parameters are already well-documented in the schema. The description groups them into categories (keyword, council, etc.) but adds no additional semantics beyond the schema. Baseline 3 is appropriate.

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

Purpose4/5

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

Clearly states it searches UK planning applications by various criteria, listing the fields returned. However, it does not explicitly distinguish itself from sibling tools like nearby_planning_applications or get_planning_application, which have distinct purposes.

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?

Provides concrete example queries ('recent planning applications in Camden', 'refused extensions in OX1') that illustrate appropriate use cases. Does not include when-not-to-use or alternatives, but the examples give clear context.

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

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.

4 tool updatesv0.1.2Jul 6, 2026
- First observedget_planning_application
- First observedlist_councils
- First observednearby_planning_applications
- First observedsearch_planning_applications

Install Server

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A3.9/5.0

Disambiguation5/5

Each tool has a clearly distinct purpose: fetching by ID, listing councils, spatial search, and keyword search. No overlap in functionality.

Naming Consistency4/5

Most names follow a verb_noun pattern (get, list, search), but 'nearby_planning_applications' omits a verb, creating a slight inconsistency. Otherwise snake_case is used consistently.

Tool Count5/5

Four tools cover the core needs of the domain (search, detail retrieval, council reference) without excess or deficiency.

Completeness4/5

The set covers essential read operations: keyword search, spatial search, and detail retrieval. A minor gap is the lack of a tool to get an application by reference number, but most workflows are supported.

Maintenance

ActivitySlowing

ResponsivenessSyncing

Resources

Need Help?

Related Servers

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

postcodeproperty
io.github.markhahnel
UK area & property intelligence for AI agents: reports, EPC, comparables, with source provenance.
Real Estate Search Open Data
1
nyc-property-intel
io.github.ccedacero
MCP server giving Claude AI access to 22+ NYC public-record databases for real estate due diligence
Real Estate Government Data
27
Airbyte Agents
io.github.airbytehq
Let AI agents query data and act across all your business apps via MCP.
Data Platforms AI & Machine Learning RAG Systems
2
agentdocs
io.github.dancourse
An agent-first office suite Claude & ChatGPT read and write over one MCP URL.
Workplace & Productivity Documentation Access
2

Related MCP Servers

Dilix MCPofficial
Real Estate Finance Government Data
Dilix-Ai
A
license
A
quality
C
maintenance
Open-source MCP server providing real estate regulatory intelligence (zoning, permits, entitlements, deal scoring) for US properties, enabling AI agents to access 10 callable tools.
Updated 3 months ago (2026-06-15 05:06 UTC)
12
15
MIT
UK Property Intelligence
Real Estate Government Data Search
paulieb89
A
license
Not graded
quality
B
maintenance
UK property data MCP server for AI hosts (Claude, ChatGPT). Wraps Land Registry, Rightmove, EPC, rental yields, stamp duty, and Companies House into 13 tools.
Updated 2 months ago (2026-07-17 10:37 UTC)
2
MIT
UK Parliament MCP Server
Government Data Open Data
ChrisBrooksbank
A
license
Not graded
quality
B
maintenance
An MCP server that gives AI assistants access to UK Parliament data. Query MPs, Lords, bills, votes, committees, debates, and more through AI assistants like Claude Desktop and VS Code Copilot.
Updated 2 months ago (2026-06-21 13:17 UTC)
4
MIT
civic-library-mcp
Government Data Open Data Location Services
adriancisnerosspeed-hub
A
license
A
quality
B
maintenance
An MCP server that gives AI agents clean, token-efficient access to US civic & property data — geocoding, census tracts, Opportunity Zones, ACS demographics, and FEMA flood zones — sourced entirely from free federal open data.
Updated 3 months ago (2026-06-16 05:21 UTC)
5
52
1
MIT

Latest Blog Posts

Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)
By Om-Shree-0709 on July 25, 2026.
mcp
Agent Identity
OAuth 2.1
Your AI Chatbot Just Exposed Your CEO's Salary to an Intern
By Om-Shree-0709 on July 2, 2026.
Agent Identity
MCP Security
OAuth Delegation
Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)
By Om-Shree-0709 on June 30, 2026.
Agentic Ai
Prompt Injection
WebAssembly

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/beshogun/planwire-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server

PlanWire MCP Server

What MCP Is

Install

Claude Desktop

Claude Code

Cursor

Tools

Example Prompts

Limits And Pricing

Troubleshooting

Development

Available Tools

Tool Schema Changelog

Maintenance

Resources

Looking for Admin?

Related MCP Connectors

Related MCP Servers

Dilix MCPofficial

Latest Blog Posts

MCP directory API