How do I use ams360-mcp-server?

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., "@ams360-mcp-server search for client with name 'Smith'" 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.

ams360-mcp-server

by Scottpedia0

Overview Schema Related Servers Score Discussions

TypeScript

Remote

AMS360 MCP Server

MCP server for Vertafore AMS360 WSAPI v3, implemented in TypeScript with @modelcontextprotocol/sdk and a real SOAP 1.1 client for AMS360's WCF endpoint.

What it does

This server exposes the following MCP tools:

search_clients(query)
get_client(clientId)
get_policies(clientId)
get_renewals(startDate, endDate)
get_activities(filter)

Under the hood it uses the public AMS360 WSAPI v3 contract:

Login to establish a session
CustomerGetById
CustomerGetByNumber
CustomerGetListByNamePrefix
PolicyGet
PolicyGetListByCustomerId
PolicyGetListByCustomerNumber
PolicyGetListByPolicyNumber
CustomerSuspenseGetListByCustomerId
CommonSuspenseGetListByEntityId
PersonalNoteGetList
LineOfBusinessGetByCode

Related MCP server: TeamDesk MCP Server

Important WSAPI notes

The public Vertafore AMS360 WSAPI v3 docs currently describe a single SOAP endpoint:

https://wsapi.ams360.com/v3/WSAPIService.svc

Authentication is not plain REST-style auth. The documented flow is:

Call Login with AgencyNo, LoginId, Password, and optionally EmployeeCode.
Read the WSAPISession SOAP header from the login response.
Send that WSAPISession header with subsequent requests.

This server follows that flow and also supports optional HTTP Basic auth for agencies that place WSAPI behind an additional HTTPS auth layer.

Limitations from the public docs

Two of the requested concepts are not fully exposed by the current public WSAPI v3 surface:

The docs show CustomerActivityInsert and CommonActivityInsert, but not an activity-list retrieval operation.
The docs do not publish a global agency-wide renewal date-range query.

Because of that:

get_activities is implemented against the retrievable WSAPI entities that agencies commonly use for reminders: customer suspenses, common suspenses, and personal notes.
get_renewals returns a structured docs-based limitation message instead of pretending a complete renewal feed exists when it does not.

Prerequisites

Node.js 20+ recommended
AMS360 WSAPI credentials created in AMS360
Your agency number

Install

npm install
npm run build

To run directly from source during development:

npm run dev

To run the compiled server:

npm start

Configuration

Set these environment variables:

export AMS360_AGENCY_NO="YOUR_AGENCY_NO"
export AMS360_USERNAME="YOUR_WSAPI_LOGIN_ID"
export AMS360_PASSWORD="YOUR_WSAPI_PASSWORD"
export AMS360_ENDPOINT_URL="https://wsapi.ams360.com/v3/WSAPIService.svc"

Optional variables:

export AMS360_EMPLOYEE_CODE="ABC"
export AMS360_TIMEOUT_MS="30000"
export AMS360_POLICY_DETAIL_LIMIT="25"
export AMS360_DEBUG="false"

Optional HTTP Basic auth, if your agency front-ends WSAPI with another auth layer:

export AMS360_HTTP_AUTH_MODE="basic"
export AMS360_HTTP_USERNAME="basic-auth-user"
export AMS360_HTTP_PASSWORD="basic-auth-password"

Aliases supported by this server:

AMS360_AGENCY_URL as an alias for AMS360_ENDPOINT_URL
AMS360_LOGIN_ID as an alias for AMS360_USERNAME

Claude Desktop

Add the server to claude_desktop_config.json:

{
  "mcpServers": {
    "ams360": {
      "command": "node",
      "args": [
        "/absolute/path/to/ams360-mcp-server/dist/index.js"
      ],
      "env": {
        "AMS360_AGENCY_NO": "YOUR_AGENCY_NO",
        "AMS360_USERNAME": "YOUR_WSAPI_LOGIN_ID",
        "AMS360_PASSWORD": "YOUR_WSAPI_PASSWORD",
        "AMS360_ENDPOINT_URL": "https://wsapi.ams360.com/v3/WSAPIService.svc"
      }
    }
  }
}

If you want Claude Desktop to launch it from the package directory instead:

{
  "mcpServers": {
    "ams360": {
      "command": "npx",
      "args": [
        "tsx",
        "/absolute/path/to/ams360-mcp-server/src/index.ts"
      ],
      "env": {
        "AMS360_AGENCY_NO": "YOUR_AGENCY_NO",
        "AMS360_USERNAME": "YOUR_WSAPI_LOGIN_ID",
        "AMS360_PASSWORD": "YOUR_WSAPI_PASSWORD"
      }
    }
  }
}

Claude Code

Add the same server definition to .claude.json:

{
  "mcpServers": {
    "ams360": {
      "command": "node",
      "args": [
        "/absolute/path/to/ams360-mcp-server/dist/index.js"
      ],
      "env": {
        "AMS360_AGENCY_NO": "YOUR_AGENCY_NO",
        "AMS360_USERNAME": "YOUR_WSAPI_LOGIN_ID",
        "AMS360_PASSWORD": "YOUR_WSAPI_PASSWORD",
        "AMS360_ENDPOINT_URL": "https://wsapi.ams360.com/v3/WSAPIService.svc"
      }
    }
  }
}

Tool behavior

`search_clients(query)`

Best-effort search strategy:

GUID -> CustomerGetById
numeric string -> CustomerGetByNumber
text -> CustomerGetListByNamePrefix
policy-looking string -> PolicyGetListByPolicyNumber, then hydrate matched customer records

`get_client(clientId)`

Fetches a full customer record by:

customer GUID, or
customer number

`get_policies(clientId)`

Returns:

policy summaries for all matched policies
hydrated policy details for up to AMS360_POLICY_DETAIL_LIMIT policies
line-of-business enrichment via LineOfBusinessGetByCode

Important:

policy summaries are returned for all matched policies
full PolicyGet detail is only fetched for the first AMS360_POLICY_DETAIL_LIMIT policies
the default detail limit is 25
the tool output includes detailHydrationTruncated and detailHydrationMessage when the detailed set is partial

`get_activities(filter)`

Supported filter routes:

{"customerId":"<guid>"} -> CustomerSuspenseGetListByCustomerId
{"entityId":"<id>","entityType":<short>} -> CommonSuspenseGetListByEntityId
{"source":"personalNotes","dateFrom":"2026-01-01","dateTo":"2026-01-31"} -> PersonalNoteGetList

Important:

this tool does not default to personal notes when the filter is empty
to retrieve personal notes, set source to "personalNotes" explicitly

`get_renewals(startDate, endDate)`

Returns a structured limitation response explaining that the public WSAPI v3 docs do not expose a true agency-wide renewal date-range query. This is returned as a normal tool response, not a transport/tool failure.

References

Vertafore AMS360 API introduction: link.vertafore.com/VERTAFORE/documentation/AMS360/introduction
AMS360 WSAPI setup help: help.vertafore.com/AMS360/content/contextsensitive/download-integration/cswebserviceapisetup.htm
AMS360 developer portal TOC: api.apps.vertafore.com/.../entities/AMS360/toc
AMS360 WSAPI bundle metadata: api.apps.vertafore.com/.../entities/AMS360/docs/AMS360:WSAPI:22f503

Available Tools

5 tools

get_activitiesGet ActivitiesB

Retrieve the documented AMS360 activity-adjacent entities available in WSAPI v3: customer suspenses, common suspenses, and personal notes.

ParametersJSON Schema

Name	Required	Description	Default
`filter`	Yes

TDQS

B3.3/5.0

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 of behavioral disclosure. It states the scope of entities returned but does not reveal behavior such as required authentication, default filtering behavior, pagination, or return format. 'Retrieve' implies a read operation, but this is not explicit.

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 that immediately states the verb and resource, followed by a precise list of entities. No wasteful words or redundancy.

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 the tool has a nested filter object with many properties, no output schema, and no annotations, the description is too sparse. It does not clarify required filter fields, the meaning of each sub-parameter, or the shape of the response, leaving significant gaps for an agent to invoke it correctly.

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

Parameters2/5

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

Schema description coverage is 0%, and the description does not explain the 'filter' object or any of its nested properties. It merely lists entity type names that map indirectly to the source enum, but it does not clarify how to use dates, IDs, or boolean flags in the filter.

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 uses a specific verb ('Retrieve') and names a precise resource: the documented AMS360 activity-adjacent entities available in WSAPI v3. It further enumerates the entity types (customer suspenses, common suspenses, personal notes), which clearly distinguishes it from sibling tools like get_client and get_policies.

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 when to use the tool by focusing on activity-adjacent entities, but it does not explicitly state when to choose this over siblings, nor does it mention any exclusions or alternatives. There is no explicit when-to-use guidance beyond the implied domain.

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

get_clientGet ClientA

Fetch a full AMS360 customer record by customer GUID or customer number.

ParametersJSON Schema

Name	Required	Description	Default
`clientId`	Yes

TDQS

A4/5.0

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 states the action ('Fetch') which implies a read operation, and 'full record' suggests complete data. However, it does not disclose potential errors, authentication needs, or what 'full' includes, beyond the basic operation.

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 concise sentence that uses no unnecessary words. It is front-loaded with the action and resource, followed by the lookup keys, making it easy to parse.

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 a simple get-by-identifier tool with one parameter and no output schema, the description is largely complete. It conveys the essential function and the key input. It could mention using search_clients when an identifier is not known, but this is a minor gap given the tool's simplicity.

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?

Schema coverage is 0%, and the description clarifies that the sole parameter (clientId) accepts either a customer GUID or a customer number. This adds meaningful semantic information not present in the schema, though it could be more explicit about formatting or type 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 uses a specific verb ('Fetch') and clearly identifies the resource ('full AMS360 customer record') and the lookup keys ('customer GUID or customer number'). It distinguishes this from sibling tools like search_clients and get_policies by focusing on direct retrieval by identifier.

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 you have a customer GUID or number, but it does not explicitly state when to prefer this over search_clients or other alternatives. There is no exclusion or alternative mentioned, so it relies on inference from the parameter and tool name.

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

get_policiesGet PoliciesA

Fetch policy summaries and hydrated policy details for an AMS360 customer GUID or customer number.

ParametersJSON Schema

Name	Required	Description	Default
`clientId`	Yes

TDQS

A4.2/5.0

Behavior3/5

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

No annotations are present, so the description carries the burden of behavioral disclosure. It indicates a fetch/read operation and mentions return types, but does not detail permissions, errors, or rate limits. This is a moderate disclosure but not a major gap.

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, front-loaded sentence that states the action, resource, and accepted identifier types with 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?

For a simple one-parameter read tool, the description adequately covers the core function and output shape (summaries and hydrated details). While there is no output schema or explicit mention of pagination, the description is sufficient for a straightforward fetch operation.

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?

The input schema only defines clientId as a required string with minLength. The description adds meaningful semantics by explaining that clientId can be a customer GUID or customer number, which the schema alone does not convey. It does not specify exact format or validation, so not a 5.

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 uses a specific verb ('Fetch') and resource ('policies') with qualifiers ('for an AMS360 customer GUID or customer number'), clearly stating what the tool does. This distinguishes it from sibling tools like search_clients and get_client, which target different resources.

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 clear context: use this tool when you need policy summaries or hydrated details for a specific customer by GUID or number. It does not explicitly name alternatives or when-not conditions, but the scope is unambiguous.

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

get_renewalsGet RenewalsD

Explain the current public WSAPI limitation around global renewal-range retrieval for AMS360.

ParametersJSON Schema

Name	Required	Description	Default
`endDate`	Yes
`startDate`	Yes

TDQS

D1.1/5.0

Behavior1/5

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 no behavioral traits such as whether the tool retrieves data, its side effects, or limitations. The mention of a 'limitation' is vague and does not describe the tool's behavior.

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

Conciseness2/5

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

The description is a single sentence, but it is not concise in a useful way—it is under-specified and fails to communicate the tool's purpose. It is not front-loaded with the core action; instead, it presents a confusing statement.

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

Completeness1/5

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

Given the simple two-parameter tool with no output schema or annotations, the description should explain basic usage or return values. It provides none of this, leaving the agent completely uninformed about how to invoke or interpret the tool.

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

Parameters1/5

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

The schema defines startDate and endDate as plain strings with no descriptions. The tool description does not mention these parameters or clarify their format, meaning, or relationship. With 0% schema description coverage, the description fails to compensate.

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

Purpose1/5

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

The description does not state what the tool does. It reads as an instruction to 'Explain the current public WSAPI limitation' rather than describing a get_renewals operation. This is misleading and fails to identify the tool's purpose.

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

Usage Guidelines1/5

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

There is no guidance on when to use this tool versus sibling tools like search_clients or get_policies. The description does not mention any context, prerequisites, or exclusions.

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

search_clientsSearch ClientsA

Search AMS360 clients by name prefix, customer number, GUID, or policy number.

ParametersJSON Schema

Name	Required	Description	Default
`query`	Yes

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 disclose behavioral traits. It lists searchable fields but omits critical details such as whether matching is exact or partial, the return format, pagination, or behavior with no results. This is a significant gap for a search tool.

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, front-loaded sentence with no redundant phrases. It efficiently conveys the tool's purpose and search parameters.

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?

Despite the simple schema, the description lacks essential context such as return format, result limits, or guidance on how to handle multiple matches. With no output schema and no annotations, the description is not enough for an agent to confidently invoke the tool and interpret results.

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?

The input schema only defines 'query' as a string with no description (0% schema coverage). The description compensates by specifying that the query can be a name prefix, customer number, GUID, or policy number, adding valuable meaning to the parameter.

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 searches AMS360 clients, with specific search criteria (name prefix, customer number, GUID, or policy number). This distinguishes it from sibling tools like get_client, which retrieves a specific client, and get_policies, which handles policies.

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 for finding clients by various identifiers but does not explicitly contrast with alternatives or state when not to use it. Since sibling tools like get_client exist, some usage context is provided, but no direct guidance is given.

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.

5 tool updatesv0.1.0Aug 2, 2026
- First observedget_activities
- First observedget_client
- First observedget_policies
- First observedget_renewals
- First observedsearch_clients

Install Server

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

TDQS

B3/5.0

Disambiguation5/5

Each tool targets a distinct resource or action: search_clients for finding clients, get_client for a full record, get_policies for policy data, get_renewals for explaining a limitation, and get_activities for activity-adjacent entities. There is no meaningful overlap.

Naming Consistency5/5

All tool names follow a consistent verb_noun pattern: search_clients, get_client, get_policies, get_renewals, get_activities. The pattern is predictable and uniform.

Tool Count5/5

The server has 5 tools, which is well within the 3-15 range for a well-scoped integration. Each tool covers a specific aspect of the AMS360 domain without unnecessary bloat.

Completeness3/5

The tool set covers core read operations for clients, policies, and activities, but get_renewals is an explanatory tool about an API limitation rather than an actual data-retrieval operation. Write/update capabilities are absent, though this may reflect the underlying API's read-only nature.

Maintenance

ActivityInactive

ResponsivenessNo issues

Resources

GitHub Repository

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

Artificial Wit AIOAuth
com.artificialwit
MCP server unifying ERPs, CRMs, APIs and knowledge base for Claude, ChatGPT and Gemini.
ERP Systems CRM Knowledge & Memory
2
Airweave SearchOAuth
io.github.airweave-ai
MCP server for searching Airweave collections with natural language queries.
Search Art & Culture Open Data
25,729
jumpcloud-genaiOAuth
com.jumpcloud
An MCP server that provides an API to LLMs to manage their JumpCloud resources.
Cloud Platforms Security Developer Tools
2
mcpOAuth
com.gibsonai
GibsonAI MCP server: manage your databases with natural language
Databases Search
233

Related MCP Servers

Open Policy Agent (OPA) REST
Shell Access Command Line Code Execution
ag2-mcp-servers
F
license
Not graded
quality
D
maintenance
An MCP Server that enables natural language interaction with the Open Policy Agent REST API, allowing users to manage policies, decisions, and data through conversational interfaces.
Updated a year ago (2025-07-16 14:21 UTC)
1
-
TeamDesk MCP Server
Databases Search
Danielbluz
A
license
Not graded
quality
D
maintenance
MCP server for TeamDesk databases, enabling CRUD operations, search, and document generation via natural language.
Updated 6 months ago (2026-03-16 21:02 UTC)
3
MIT
aha-mcp
Product Management Project Management Content Management Systems
popand
A
license
B
quality
D
maintenance
MCP server for accessing and managing Aha! records, including features, requirements, pages, and documents through natural language.
Updated a year ago (2025-07-10 18:56 UTC)
4
248
2
ISC
Business Central MCP Workshop
ERP Systems Databases
javiarmesto
F
license
Not graded
quality
D
maintenance
MCP server that integrates with Microsoft Dynamics 365 Business Central, enabling querying of customers, items, and sales orders through natural language commands in Claude Desktop.
Updated 9 months ago (2025-11-23 17:00 UTC)
10
-

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/Scottpedia0/ams360-mcp-server'

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