{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_aj7n95hu229w","handle":"iflow-mcp-sjtu-sai-agents-mcp-sandbox","url":"https://wellknown.network/agents/iflow-mcp-sjtu-sai-agents-mcp-sandbox","links":{"self":"https://wellknown.network/agents/iflow-mcp-sjtu-sai-agents-mcp-sandbox/record.json","html":"https://wellknown.network/agents/iflow-mcp-sjtu-sai-agents-mcp-sandbox","markdown":"https://wellknown.network/agents/iflow-mcp-sjtu-sai-agents-mcp-sandbox/record.md","api":"https://wellknown.network/api/v1/agents/iflow-mcp-sjtu-sai-agents-mcp-sandbox","status":"https://wellknown.network/api/v1/agents/iflow-mcp-sjtu-sai-agents-mcp-sandbox/status","claim":"https://wellknown.network/agents/iflow-mcp-sjtu-sai-agents-mcp-sandbox/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/iflow-mcp-sjtu-sai-agents-mcp-sandbox/claim.json","badge":"https://wellknown.network/agents/iflow-mcp-sjtu-sai-agents-mcp-sandbox/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/iflow-mcp-sjtu-sai-agents-mcp-sandbox/history","tools":"https://wellknown.network/api/v1/agents/iflow-mcp-sjtu-sai-agents-mcp-sandbox/tools"},"ard":{"identifier":"urn:air::server:iflow-mcp-sjtu-sai-agents-mcp-sandbox","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"iflow-mcp_sjtu-sai-agents-mcp_sandbox","summary":"A code execution server with MCP support","description":"# Code Execution Server\n\nThis repository provides a basic implementation of a **code execution server**, designed primarily for **Xmaster** ([paper](https://arxiv.org/abs/2507.05241), [code](https://github.com/sjtu-sai-agents/X-Master)) and **Browse Master** ([paper](https://arxiv.org/abs/2508.09129) [code](https://github.com/sjtu-sai-agents/Browse-Master)). The full implementation is used in [SciMaster](https://scimaster.bohrium.com). \n\nDue to the proprietary nature of the full code, this repository only includes an **open-source framework** and the **basic components** required for code execution. It also includes a simple **network search tool** implementation.\n\n> **⚠️ Warning**: This is a basic code execution server without virtualization or safety protections. For added security, consider running it within **Docker** or **Apptainer** containers as necessary.\n\n---\n\n## 🛠️ Setup\n\n### Environment\n\nClone this repository and navigate to the project directory and install the required dependencies:\n\n```bash\ncd mcp_sandbox/\npip install -r requirements.txt\n```\n\n### Tools\n\n- setup the serper key in `configs/web_agent.json`\n- setup the models' api key in `configs/llm_call.json`\n\n---\n\n## 🚀 Deploy the Code Execution Server\n\n### Step 1: Start the API Server\n\nWe will first start the API server used by the tools. This API server proxies all search-related services, including:\n\n- [Serper](https://serper.dev/)'s Google Search Service\n- A series of Model APIs\n\nNavigate to the api_proxy directory and start the API server:\n```bash\ncd api_proxy\npython api_server.py\n```\n\n### Step 2: Deploy the Server\n\nDeploy the server by running the following script in the `MCP` directory:\n\n```bash\ncd MCP\nbash deploy_server.sh\n```\n\n---\n\n## 📝 Usage\n\n### Sending a Request\n\nTo send a request to the server, use the following `curl` command:\n\n```bash\ncurl -X POST \"http://<your-server-url>/execute\" \\\n     -H \"Content-Type: application/json\" \\\n     -d '{\"code\": \"<your code here>\"}'\n```\n\n### ⚡ Benchmarki…","publisher":null,"homepage":null,"repository":null,"version":"0.1.0","license":null,"protocols":["mcp"],"tags":["mcp"],"pricing":null,"endpoints":[{"url":"pypi:iflow-mcp_sjtu-sai-agents-mcp_sandbox","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","summary":"pypi","version":"pypi","description":"pypi"}},"derived":{"capabilities":[{"slug":"code.execution","name":"Code Execution","confidence":1,"provenance":"derived"},{"slug":"dev.version-control","name":"Version Control","confidence":0.825,"provenance":"derived"},{"slug":"dev.ci-cd","name":"CI/CD & Deploy","confidence":0.733,"provenance":"derived"}],"categories":["code","dev"],"language":"en"},"observed":{"status":"unknown","statusReason":"Distributed as a package to run locally; no network endpoint to check.","lastOkAt":null,"lastProbedAt":null,"statusComputedAt":null,"reliability30d":null,"latestObservations":[],"tools":null,"package":{"name":"iflow-mcp_sjtu-sai-agents-mcp_sandbox","registry":"pypi","observedAt":"2026-09-15T20:21:22.134Z","publishedAt":"2026-01-27T08:41:52.663902Z","latestVersion":"0.1.0"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"iflow-mcp_sjtu-sai-agents-mcp_sandbox","url":"https://pypi.org/project/iflow-mcp_sjtu-sai-agents-mcp_sandbox/","firstSeenAt":"2026-09-09T21:23:55.162Z","fetchedAt":"2026-09-15T20:19:37.838Z","normalizedAt":"2026-09-15T20:19:37.838Z"}]},"firstSeenAt":"2026-09-09T21:23:55.162Z","updatedAt":"2026-09-15T20:21:22.134Z"}