Optimize
Secure
The #1 agentic semantic tool search: 91.6% first-try accuracy on S1 Search Bench • Explore Tool Discovery →
Connect your AI agent to StackOne's InvGate Asset Management MCP server and give it 64 MCP tools out of the box. Auth, tool execution, and security all managed.
Coverage
Create, read, update, and delete across InvGate Asset Management — and extend your agent's capabilities with custom actions.
Authentication
Per-user OAuth in one call. Your InvGate Asset Management MCP server gets session-scoped tokens with zero credentials stored on your infra.
Agent Auth →Security
Every InvGate Asset Management tool response scanned for prompt injection in milliseconds — 88.7% accuracy, all running on CPU.
Prompt Injection Defense →Performance
Free up to 96% of your agent's context window to enhance reasoning and reduce cost, on every InvGate Asset Management call.
Tools Discovery →A InvGate Asset Management MCP server lets AI agents read and write InvGate Asset Management data through the Model Context Protocol — Anthropic's open standard for connecting LLMs to external tools. StackOne's InvGate Asset Management MCP server ships with 64 pre-built actions, fully extensible via the Connector Builder — plus managed authentication, prompt injection defense, observability, and agent execution runtime. Connect it from MCP clients like Claude Desktop, Claude Code, Cursor, Goose, and VS Code, or from agent frameworks like OpenAI Agents SDK, LangChain, and Vercel AI SDK.
Every action from InvGate Asset Management's API, ready for your agent. Create, read, update, and delete — scoped to exactly what you need.
Create an asset
Retrieves information for assets
Retrieves information for a specific asset identified by its ID
Update an asset entirely (all the attributes at the same time)
Get a list of Chromebooks
Get a specific Chromebook by its ID
Retrieves a list of cloud assets (AWS, Azure, GCP)
Retrieves a specific cloud asset by ID
List computers
Retrieve a computer
Creates a new cost center
Retrieves information for cost centers
Retrieves information for a specific cost center identified by its ID
Replaces or updates the information for a specific cost center identified by its ID
Deletes the specified cost center identified by its ID
Retrieves a list of custom fields values
Retrieves detailed information about the custom field value or values and associated configuration item
Upserts (set-if-missing, update-if-present) the value of a custom field for a specific configuration item. The composite key (`custom_field_id` + `ci_id`) identifies the entry — there is no standalone record ID. The response echoes the request fields but does not return an identifier usable with `get_custom_field_values_ci`; to re-read the value, call `list_custom_field_values_cis` and filter by `custom_field_id` and `ci_id`.
Retrieves a list of database systems (Database Instances and Databases)
Retrieves a specific database system by its ID
Retrieves financial information for assets
Retrieves financial information for a specific asset
Updates the financial information for a specific asset
Retrieves information for manufacturers
Retrieves information for a specific manufacturer identified by its ID
Creates a new person
Retrieves information for a specific person identified by its ID
Replaces or updates the properties for a specific person identified by its ID
Deletes the specified person identified by its ID
Creates a new purchase order
Retrieves purchase orders
Retrieves a specific purchase order identified by its ID
List servers
Retrieve a server
Creates a tag
Lists tags
Retrieves a tag
Creates a new contact for a vendor
Retrieves the external contact persons that belong to a specific VENDOR (requires a vendor_id). NOT for internal people/employees — to look up or update a person by name use list_people / patch_people.
Retrieves information for a specific contact from a vendor identified by its ID
Deletes a contact for a vendor, identified by its ID
Creates a new vendor
Retrieves a paginated list of vendors. NOTE - there is NO server-side name/company_name filter; the only query parameter is `page`. To resolve a vendor by name, page through the list and match `company_name` client-side (the vendor's name is in `company_name`, NOT a `name` field).
Retrieves information for a specific vendor identified by its ID
Replaces or updates the information for a specific vendor identified by its ID
Deletes the specified vendor identified by its ID
Attach a file (binary, multipart upload) to one or more CIs.
List asset types
List assets with information about related properties
Retrieve a computer's remote desktop integrations
Retrieves information for custom fields settings
Retrieves detailed financial information for assets
Retrieves information for persons
Retrieves detailed information for people
Retrieve a server's remote desktop integrations
Sets multiple values on a custom field configured to allow multiple values. ⚠ Prerequisite: the target custom field MUST be configured with "allow multiple values" in the InvGate admin console — otherwise the endpoint returns HTTP 400 "This field does not allow for multiple values." Account-level configuration, not a connector feature flag.
Update an asset partially (just some attributes)
Partially updates the information for a specific cost center identified by its ID, without affecting the entire entity
Partially update the financial information for a specific asset, without impacting the entire resource
Partially updates an internal person/employee by ID — including their contact info (email, phone, cellphone). Use this to update a named person's contact details (first resolve the id via list_people, filtering by name/email). NOT for a vendor's external contacts (use patch_vendor_contact for those).
Assigns tags to CIs
Unassigns tags to CIs
Partially updates the information for a specific vendor identified by its ID, without affecting the entire entity
Updates a contact for a vendor, identified by its ID
One endpoint. Any framework. Your agent is talking to InvGate Asset Management in under 10 lines of code.
Agent Frameworks
{
"mcpServers": {
"stackone": {
"command": "npx",
"args": [
"-y",
"mcp-remote@latest",
"https://api.stackone.com/mcp?x-account-id=<account_id>",
"--header",
"Authorization: Basic <YOUR_BASE64_TOKEN>"
]
}
}
}Anthropic's code_execution processes data already in context. Custom MCP code mode keeps raw tool responses in a sandbox. 14K tokens vs 500.
11 min
Benchmarking BM25, TF-IDF, and hybrid search for MCP tool discovery across 916 tools. The 80/20 TF-IDF/BM25 hybrid hits 21% Top-1 accuracy in under 1ms.
10 min
MCP tools that read emails, CRM records, and tickets are indirect prompt injection vectors. Here's how we built a two-tier defense that scans tool results in ~11ms.
12 min
MCP vs A2A: what each protocol standardizes, how they differ, their shared security risks including indirect prompt injection, and when to use one, both, or a hybrid architecture.
12 min
MCP wraps APIs, it doesn't replace them. After building 200+ connectors that serve both, here's when each approach wins.
14 min read
origin_owner_id.All the tools you need to build and scale AI agent integrations, with best-in-class connectivity, execution, and security.