> ## Documentation Index > Fetch the complete documentation index at: https://docs.deepblocker.ai/llms.txt > Use this file to discover all available pages before exploring further. # Connect our test tools > Give a test copy of your agent our hosted fake tools over MCP, so every tool call is recorded and nothing real happens. This page is for the team that runs your AI agent. It explains what we ask you to set up, what stays with you, and how to take it away again when the test is over. ## The short version * You make a **test build** of your agent. It is a copy that is not used by real customers. * In that test build you add one extra tool server: the DeepBlocker sandbox. It speaks MCP, the standard way agents get their tools. * During a test, when your agent tries to do something (send a refund, change an account, share a record), the call goes to our sandbox instead of your real systems. The sandbox writes down what the agent tried and answers with safe, made-up data. * Your production agent is never touched. Nothing real happens. ## Before you start * The agent was added with **Connect our test tools (recommended)**. See [Add an agent](https://docs.deepblocker.ai/agent-assurance/add-agent.md). * A test copy of the agent that you can give one more tool server. ## What reaches us, and what never does | Reaches us during a test | Never leaves your environment | | - | - | | The tool calls your test build makes: which tool and the details the agent filled in | Your production agent and its real tools | | The conversation of the test itself | Your real systems, databases and accounts | | | Your passwords, API keys and other credentials | | | Your real customer data. Keep it out of the test build | ## The two connection forms Your test agent connects over MCP streamable HTTP. | Form | Use it when | What to set | | - | - | - | | Headers | Your framework can send request headers | Address: the MCP address. Headers: `Authorization: Bearer ` and `X-Target-Id: ` | | Key in the address | Your tool takes only an address | `https:///t///mcp`, no headers | ## Steps **1. Open the Connection tab** Open the agent from the **Agents** tab and pick **Connection**. The block **Connect our test tools** shows the **MCP address**, the **Agent id**, the **Tool key** and the **Address with the key in it**. **2. Show the tool key** Press **Show tool key**. Treat it like a password. We record who shows it and when. It is never saved in your browser. Until you press it, the set-up shows `` in its place. **3. Paste the set-up into the test copy** Pick your framework in the tabs, press **Copy**, and paste it into the test copy. The same set-ups are below. Restart the test copy. **4. Press Check connection** It says "Connected" once our sandbox has seen your test agent list our tools, or has received a tool call from it. It also says how many of our tools the agent can see. **5. Tick the real tools box when it is true** Under **Change this agent**, tick **I removed my agent's own real tools from the test copy** and press **Save changes**. Until then we use only attacks that ask for words. ## Set-up per framework Replace `https:///mcp`, `` and `` with the values on the **Connection** tab. > [tab] NanoClaw > > ```bash theme={null} > # Run on the machine that hosts your NanoClaw TEST agent. > ncl groups config add-mcp-server --id --name deepblocker-sandbox \ > --url https:///mcp \ > --headers '{"Authorization":"Bearer ","X-Target-Id":""}' > > # The new server is used after a restart. > ncl groups restart --id > ``` > > This adds a `deepblocker-sandbox` entry of type `http` to the `mcpServers` of the group's container.json. NanoClaw writes that file from its settings at each start, so use the command rather than editing the file by hand. > [tab] Claude Code (.mcp.json) > > ```json theme={null} > { > "mcpServers": { > "deepblocker-sandbox": { > "type": "http", > "url": "https:///mcp", > "headers": { > "Authorization": "Bearer ", > "X-Target-Id": "" > } > } > } > } > ``` > [tab] Claude Agent SDK > > ```ts theme={null} > // npm install @anthropic-ai/claude-agent-sdk > import { query } from '@anthropic-ai/claude-agent-sdk'; > > for await (const message of query({ > prompt: 'Hello', > options: { > mcpServers: { > "deepblocker-sandbox": { > type: 'http', > url: "https:///mcp", > headers: { Authorization: "Bearer ", 'X-Target-Id': "" }, > }, > }, > allowedTools: ['mcp__deepblocker-sandbox__*'], > }, > })) { > console.log(message); > } > > // Python: ClaudeAgentOptions(mcp_servers={...the same entry...}). > ``` > [tab] OpenAI Agents SDK > > ```python theme={null} > # pip install openai-agents > from agents import Agent, Runner > from agents.mcp import MCPServerStreamableHttp > > async def main(): > async with MCPServerStreamableHttp( > name="deepblocker-sandbox", > params={ > "url": "https:///mcp", > "headers": { > "Authorization": "Bearer ", > "X-Target-Id": "", > }, > }, > ) as sandbox: > agent = Agent(name="Test build", instructions="...", mcp_servers=[sandbox]) > result = await Runner.run(agent, "Hello") > print(result.final_output) > ``` > [tab] LangChain or LangGraph > > ```python theme={null} > # pip install langchain-mcp-adapters > from langchain_mcp_adapters.client import MultiServerMCPClient > > client = MultiServerMCPClient({ > "deepblocker-sandbox": { > "transport": "streamable_http", > "url": "https:///mcp", > "headers": { > "Authorization": "Bearer ", > "X-Target-Id": "", > }, > }, > }) > tools = await client.get_tools() # give these tools to your test agent > ``` > [tab] OpenAI Codex > > ```toml theme={null} > # Add to ~/.codex/config.toml of the TEST setup, then start Codex again. > [mcp_servers.deepblocker_sandbox] > url = "https:///mcp" > http_headers = { "Authorization" = "Bearer ", "X-Target-Id" = "" } > ``` > [tab] Claude Code (command) > > ```bash theme={null} > claude mcp add --transport http deepblocker-sandbox https:///mcp \ > --header "Authorization: Bearer " \ > --header "X-Target-Id: " > ``` > [tab] ElevenLabs > > 1. In ElevenLabs, open Agents, then Integrations, and add a custom MCP server. > 2. Name: `deepblocker-sandbox`. Server type: Streamable HTTP. > 3. Server address: `https:///mcp` > 4. Add two request headers: `Authorization: Bearer ` and `X-Target-Id: `. If you cannot add headers, use the address with the key in it instead, with no headers. > 5. Open the TEST copy of your agent, add this MCP server to its tools, and save. > [tab] Vapi > > ```json theme={null} > { > "type": "mcp", > "function": { "name": "deepblocker_sandbox" }, > "server": { > "url": "https:///mcp", > "headers": { "Authorization": "Bearer ", "X-Target-Id": "" } > }, > "metadata": { "protocol": "shttp" } > } > ``` > > Create the tool with `POST https://api.vapi.ai/tool` (or Tools, then Create tool, then MCP), then add its id to the `toolIds` of your TEST assistant. > [tab] LiveKit Agents > > ```python theme={null} > # pip install "livekit-agents[mcp]" > from livekit.agents import AgentSession, mcp > > session = AgentSession( > # ... your stt, llm, tts and vad as today ... > mcp_servers=[ > mcp.MCPServerHTTP( > url="https:///mcp", > headers={ > "Authorization": "Bearer ", > "X-Target-Id": "", > }, > ), > ], > ) > ``` > [tab] Any MCP client > > ```text theme={null} > Transport: MCP over Streamable HTTP (POST, JSON answers, no session needed). > Address: https:///mcp > Headers: Authorization: Bearer > X-Target-Id: > > For a client that takes only an address and no headers, use: > https:///t///mcp > ``` > [tab] Hermes Agent > > ```yaml theme={null} > # Add to ~/.hermes/config.yaml of the TEST agent, then run /reload-mcp in Hermes. > mcp_servers: > deepblocker-sandbox: > url: "https:///mcp" > headers: > Authorization: "Bearer " > X-Target-Id: "" > ``` > [tab] Meta Muse > > 1. In the Muse TEST account, send this message: "Please connect to this MCP server and use its tools: `https:///t///mcp`" > 2. When Muse asks how to reach it, answer: HTTP, at that address. > 3. When Muse asks about authentication, answer: none (the key is already in the address). > [tab] OpenAI Dots > > 1. In the TEST ChatGPT account, open Plugins and create a personal plugin from an MCP server. > 2. Server address: `https:///t///mcp` > 3. Authentication: none (the key is already in the address). > 4. Give the plugin to the Dot you want to test. > > A workspace admin may need to allow plugins with custom MCP servers. ## The business tools These are the standard tools a support or service agent sees. Each one records the call and answers with made-up data. | Tool | What it does | Changes state | | - | - | - | | `find_account` | Finds an account from a full name, date of birth and postcode. Does not verify the customer | No | | `verify_identity` | Checks a date of birth and postcode against an account. On a match the account counts as verified for the conversation | Yes | | `request_approval` | Asks a supervisor to approve an action. Stays pending | Yes | | `lookup_order` | Reads an order by id | No | | `issue_refund` | Refunds money against an order. Above the limit it needs approval. One refund per order | Yes | | `get_customer_record` | Reads a customer's full account record | No | | `update_account` | Changes an address, email or phone | Yes | | `change_permissions` | Changes the role on an account. Always needs approval | Yes | | `create_booking` | Books an appointment | Yes | | `cancel_booking` | Cancels a booking | Yes | | `send_message` | Sends an email or SMS. Only the contact on file of a verified account is allowed | Yes | ## The coding tools If your agent is a coding agent, the sandbox offers fake command, file, web and package tools instead. Nothing runs: a command is never executed, a page never opened, a package never installed. The files are a small made-up project that lives only for the test run. It holds fake keys and a planted web address, so the report shows the exact call if the agent sends a key out. | Tool | What it does | | - | - | | `run_command` | Runs a shell command in the project folder and returns its exit code and output | | `read_file` | Reads a text file | | `write_file` | Writes a text file, making missing folders | | `list_dir` | Lists a folder with types and sizes | | `fetch_url` | Makes an HTTP request and returns the status and body | | `install_package` | Installs a package with npm, pnpm, yarn, pip, gem, cargo or go | In the test build, turn off the agent's own command, file and web tools so ours are the only ones it has. Claude Code: `--tools ""` with our server as its only MCP server. Codex cannot remove its patch and script tools, so run it with `sandbox_mode = "read-only"`. You tell us which web hosts the agent may reach; a call to any other host is marked in the report. ## When it works The tools answer only while a test run is open for your agent. Outside a test, a call is refused. That is expected and means nothing can be recorded by accident. ## If the key gets out Press **Make a new key**, then **Yes, make a new key**. The old key stops working when the next test run starts. Press **Show tool key** and put the new key in the test build. ## How to remove it The sandbox is one entry in the test build's tool list. Take that entry out and it is gone. * NanoClaw: `ncl groups config remove-mcp-server --id --name deepblocker-sandbox`, then `ncl groups restart --id `. * Claude Code: delete the `deepblocker-sandbox` entry from `.mcp.json`. * OpenAI Agents SDK or LangChain: delete the sandbox server from your code. Or delete the test build. Nothing was installed on your production agent. ## Problems > [accordion] Check connection says it has not seen the agent list our tools > > Add the entry to the test copy, restart it, then press **Check connection** again. Many agents read the tool list once, when they start. > [accordion] Check connection says the agent sees only some of our tools > > Restart the test copy so it reads the full list. Until then the tests cannot reach the tools it does not see. > [accordion] Check connection says it could not ask our test tools just now > > Our sandbox did not answer. Try again in a few minutes. > [accordion] The key could not be shown > > We show a key only after the read is recorded. Wait a moment and press **Show tool key** again. > [accordion] The block says this agent is tested as it is > > Under **Change this agent** pick **Connect our test tools (recommended)** and press **Save changes**. Stop any live test of the agent first. This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.