Connect
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 Gladly MCP server and give it 65 MCP tools out of the box. Auth, tool execution, and security all managed.
Coverage
Create, read, update, and delete across Gladly — and extend your agent's capabilities with custom actions.
Authentication
Per-user OAuth in one call. Your Gladly MCP server gets session-scoped tokens with zero credentials stored on your infra.
Agent Auth →Security
Every Gladly 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 Gladly call.
Tools Discovery →A Gladly MCP server lets AI agents read and write Gladly data through the Model Context Protocol — Anthropic's open standard for connecting LLMs to external tools. StackOne's Gladly MCP server ships with 65 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 Gladly's API, ready for your agent. Create, read, update, and delete — scoped to exactly what you need.
Retrieve a list of agents in Gladly.
Retrieve a single agent profile by ID.
Retrieve the active call recording status for an agent.
Update the active call recording status for an agent.
Search public answers by query string.
Retrieve the first 1000 public answers sorted alphabetically.
Retrieve a single public answer by ID.
Create a new answer in Gladly.
Retrieve all answers in the organization.
Retrieve a single answer by ID.
Update an existing answer by ID.
Delete an answer by ID.
Retrieve the content of an answer by language and type.
Delete the content of an answer for a specific language and type.
Create a new business hours configuration.
Retrieve a list of business hours configurations.
Retrieve a single business hours configuration by ID.
Update an existing business hours configuration.
Delete a business hours configuration by ID.
Retrieve conversation metadata by ID.
Update the assignee or status of a conversation.
Add a conversation item to a customer's timeline.
Retrieve all items in a conversation timeline.
Retrieve a single conversation item by ID.
Delete a conversation item by ID.
Add a conversation item to an existing customer's timeline.
Delete a conversation item for a specific customer.
Add an internal note to a conversation.
Retrieve a specific note from a conversation.
Create a new customer profile in Gladly.
Retrieve a customer profile by ID.
Update a customer profile by ID.
Delete a customer and all associated conversations.
Create a new task for a customer.
Retrieve a list of tasks for a customer.
Retrieve a single task by ID.
Update an existing task by ID.
Add a comment to an existing task.
Retrieve all comments for a task.
Retrieve a single task comment by ID.
Retrieve a list of teams in Gladly.
Retrieve a single team by ID.
Create a new topic in Gladly.
Retrieve a list of topics in Gladly.
Retrieve a single topic by ID.
Update an existing topic by ID.
Add or update the content of an answer for a specific language and type.
Send an SMS message to a customer.
Send an email message to a customer.
Add topics to a conversation.
Create a new recipient collection for an existing proactive campaign.
Add a task to an existing customer's conversation timeline.
Retrieve a list of audiences in Gladly.
Retrieve all conversations for a customer.
Retrieve the media recording file for a conversation item.
Retrieve the voice transcript for a phone call or voicemail.
Retrieve a redirect URL for an attachment on a conversation item.
Retrieve a stream of events from Gladly.
Retrieve a custom attribute (freeform topic) by ID.
Retrieve a list of inboxes in Gladly.
Retrieve a single inbox by ID.
Retrieve metadata about the Gladly organization.
Remove a topic from a conversation.
Send a reply to a conversation item.
Search for customers by email, phone number, or external ID.
Connect your AI agent to Gladly and help your team scale the support operations they run by hand today.
Use StackOne to connect your AI agent to your helpdesk, CRM, and messaging tools to automate ticket triage and priority routing.
ViewUse StackOne to connect your AI agent to your telephony, CRM, and messaging tools to automate voice call summarization and CRM logging.
ViewUse StackOne to connect your AI agent to your helpdesk, CRM, and messaging tools to automate SLA breach prediction and escalation.
ViewOne endpoint. Any framework. Your agent is talking to Gladly 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>"
]
}
}
}113+ actions
104+ actions
84+ actions
77+ actions
73+ actions
69+ actions
67+ actions
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.