Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Acuris MCP Server Validate this address: 10 Downing Street, London, SW1A 2AA"
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.
Model Context Protocol server for the Acuris Address Validation & Geocoding API. Plug Acuris into Claude Desktop, Claude Code, Cursor, or any MCP-aware client and your agent gains four address tools:
Tool | What it does |
| Validate any postal address in 240+ countries. Returns standardised address, rooftop coordinates, confidence score (A-F), UDPRN + UPRN for UK. |
| Given a UK postcode, return every Royal Mail PAF delivery point at it. |
| Convert an address into latitude + longitude. |
| Convert a lat/lng into the nearest known address. |
Get a free API key (100 free validations, 100 free geocodes, 7 days, no credit card) at api.acuris-geo.com/register.
Add this to claude_desktop_config.json:
{
"mcpServers": {
"acuris": {
"command": "npx",
"args": ["-y", "@acuris-geo/mcp-server"],
"env": { "ACURIS_API_KEY": "acu_…" }
}
}
}Restart Claude Desktop. The four tools appear under the "Acuris" server.
claude mcp add acuris -e ACURIS_API_KEY=acu_… -- npx -y @acuris-geo/mcp-serverThe server speaks plain stdio MCP. Point your client at:
ACURIS_API_KEY=acu_… npx -y @acuris-geo/mcp-serverRelated MCP server: Postio
After installing, try:
Validate this address: 10 Downing Street, London, SW1A 2AA
Look up every address at the UK postcode M1 1AD
What's the rooftop coordinate for the Reichstag, Berlin?
What address is at 51.5036, -0.1277?
The agent picks the right tool, calls it, and reads the JSON back to you.
No other UK / EU address-validation provider (Ideal Postcodes, Loqate, Smarty, postcoder, getaddress.io) ships an MCP server today. If your team builds with agentic IDEs, Acuris is the only AV provider that hands you a first-class integration.
The server talks to:
POST https://api.acuris-geo.com/validate
POST https://api.acuris-geo.com/postcode-lookup (GBR — proxied to paf.acuris-geo.com internally)
GET https://api.acuris-geo.com/geocode
GET https://api.acuris-geo.com/reverse
UK requests are automatically routed to our PAF satellite (paf.acuris-geo.com) where the licensed Royal Mail PAF dataset lives. The caller doesn't need to know this.
npm install
npm run build
ACURIS_API_KEY=test node dist/index.js # smoke-test with the public test keyMIT. Source: https://github.com/Acuris-GmbH/acuris-mcp-server.
Convert an address into latitude + longitude. Returns rooftop coordinates where available, falling back to street, postcode, or locality centroid (with accuracy_type indicating which).
| Name | Required | Description | Default |
|---|---|---|---|
| country | Yes | ISO 3-letter country code, e.g. `gbr`, `usa`, `deu`. | |
| street | No | ||
| house_number | No | ||
| city | No | ||
| postcode | No | ||
| state | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden. It discloses the fallback hierarchy (rooftop to centroid) and the 'accuracy_type' output field, which is valuable behavioral context. However, it does not cover error handling or rate limits.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences, no fluff, front-loaded with purpose and key behavior. Every sentence adds value.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity (6 params, no output schema, no annotations), the description explains fallback logic but omits output structure (e.g., coordinate format) and possible accuracy_type values. While clear, it leaves gaps for an agent needing full behavioral details.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is only 17% (only 'country' described). The description adds no parameter-level details about street, house_number, etc., and does not compensate for the missing parameter descriptions. Users get little guidance on which parameters are needed or optional.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses a specific verb 'Convert' and clearly identifies the resource: address to latitude+longitude. It differentiates from sibling tools like reverse_geocode, postcode_lookup, and validate_address by stating its core function.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage when an address needs geocoding, but does not explicitly state when to use this tool versus alternatives (e.g., reverse_geocode for coordinates to address). No usage 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.
Given a UK postcode, return every Royal Mail PAF delivery point at that postcode — street, house number, building, organisation, rooftop coordinates, UDPRN, and UPRN.
| Name | Required | Description | Default |
|---|---|---|---|
| postcode | Yes | A UK postcode in any format (with or without space): `SW1A 2AA`, `M11AD`, `EH1 1YZ`. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden for behavioral disclosure. It describes the input and output but does not mention error handling, rate limits, or authentication requirements. For a simple lookup, this is sufficient but not exemplary.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, well-structured sentence. It front-loads the conditional and lists the output comprehensively without any wasted words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description covers the core functionality and lists the return fields, which compensates for the lack of an output schema. It omits error handling and response format, but for a one-parameter tool this is reasonably complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, and the parameter's schema already includes a description. The tool description does not add significant semantic value beyond the schema—it simply restates 'Given a UK postcode'. Thus, baseline score of 3 applies.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: given a UK postcode, return delivery points from Royal Mail PAF. It uses specific verbs and lists the exact data returned (street, house number, etc.), distinguishing it from sibling tools like geocode or validate_address.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies when to use the tool (when you have a UK postcode and want delivery points), but it does not explicitly state when not to use it or compare it to siblings (geocode, reverse_geocode, validate_address). The guidance is adequate but lacks explicit differentiation.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Convert a latitude / longitude pair into the nearest known address. Restrict to a specific country with the optional country parameter.
| Name | Required | Description | Default |
|---|---|---|---|
| lat | Yes | Latitude (WGS84). | |
| lng | Yes | Longitude (WGS84). | |
| radius_m | No | Search radius in metres around the lat/lng. Default 100 m. | |
| country | No | Optional ISO-3 country to restrict the search. Omit to search globally. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided; description only says 'nearest known address' without detailing coverage, accuracy, or failure behavior. Missing info on search radius default and what happens if no address found.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two clear sentences with no waste. Front-loaded with core purpose, then optional parameter hint.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Tool has 4 params and no output schema. Description does not explain return format or edge cases (e.g., no result). Lacks completeness despite good schema coverage.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema covers 100% of parameters. Description adds 'Restrict to a specific country', repeating schema info. No new semantic value beyond schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Clearly states verb 'convert' and resource 'latitude / longitude pair into address'. Distinct from siblings: geocode (forward), postcode_lookup, validate_address. Explicitly mentions country restriction.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Implies usage for reverse geocoding but does not explicitly state when to use alternatives (e.g., geocode for forward). Lacks when-not-to-use guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Validate any postal address in 240+ countries against authoritative reference data. Returns standardised address, rooftop coordinates, confidence score (A-F), and UDPRN + UPRN for UK addresses.
| Name | Required | Description | Default |
|---|---|---|---|
| country | Yes | ISO 3-letter country code (preferred, e.g. `gbr`, `usa`, `deu`, `fra`). ISO-2 also accepted. | |
| input | No | Single-line address — paste the whole address as one string, e.g. `10 Downing Street, London, SW1A 2AA`. Provide this OR the fielded inputs below. | |
| street | No | Street name (fielded input). | |
| house_number | No | House / building number. | |
| city | No | City / locality. | |
| postcode | No | Postcode / ZIP. | |
| state | No | State / region — required for USA, CAN, AUS, BRA, MEX. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. It discloses that the tool validates addresses against authoritative data and returns standardized addresses, rooftop coordinates, confidence levels, and UK-specific identifiers. It does not mention error handling or edge cases, but overall behavior is well explained.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely concise—two sentences that front-load the core purpose and then enumerate key return values. Every word adds value, with no repetition of schema information or unnecessary details.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given 7 parameters and no output schema, the description covers the tool's scope (240+ countries), input alternatives, and expected outputs. It could be more complete by describing error conditions or confidence score interpretation, but it is sufficient for most use cases.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so each parameter already has a description. However, the description adds important context: it clarifies that 'input' can substitute fielded parameters and that 'state' is required for certain countries (USA, CAN, etc.), which is not evident from the schema alone.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'validate' and resource 'postal address', and distinguishes from sibling tools (geocode, postcode_lookup, reverse_geocode) by emphasizing validation against authoritative reference data and returning confidence scores and UK-specific IDs.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies the tool is for validation but does not explicitly guide when to use it over siblings like geocode or reverse_geocode. It lacks explicit 'when to use' or 'when not to use' guidance, though the context of returning confidence scores hints at its validation purpose.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
v0.1.0geocodepostcode_lookupreverse_geocodevalidate_addressEach tool has a clearly distinct purpose: geocode converts address to coordinates, reverse_geocode does the inverse, postcode_lookup provides detailed UK delivery points, and validate_address validates addresses globally. No overlap in functionality.
Names use consistent snake_case, but the verb-noun order varies slightly (e.g., 'postcode_lookup' is noun_verb while 'validate_address' is verb_noun). Still readable and predictable.
Four tools cover the essential address operations—forward/reverse geocoding, UK postcode lookup, and validation—without bloat. The count is ideal for this focused domain.
Core address workflows are covered, but missing features like address autocomplete or batch processing are minor gaps that agents can work around.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Address validation & geocoding for AI agents: 240+ countries, UK PAF, free US/CA enrichment
Geocoding, truck routing, traffic, weather, and place search via MCP — 11 hosted tools.
Google Maps MCP Pack — geocoding, places, directions, distance matrix, elevation.
350+ production-ready APIs through one MCP server — weather, geocoding, validation, financial data.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/Acuris-GmbH/acuris-mcp-server'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
