AgentSociety (tsinghua-fib-lab/AgentSociety) is an MCP server listed on the M8ven Trust Index. It scores 98 out of 100, grade A. It declares 6 tools. No publisher has claimed this listing.

Back to MCP Trust IndexM8ven
A
Trusted
98/100
7 days ago

AgentSociety

AgentSociety 2 is a modern, LLM-native agent simulation platform designed for social science research and experimental design. It provides a flexible framework for creating and managing intelligent agents in simulated environments.

→ tsinghua-fib-lab/AgentSociety· listed on github_code

Trusted. Deep verification, no outstanding findings, and an established reputation. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.

How we verified

Code Verified⚡ Live Monitored: not connected

Verified is a snapshot. Live keeps it current, and builds your track record.

⚡ Connect GitHub → continuous verification on every pushwhy connect →

Who stands behind it

tsinghua-fib-lab

Source: github_code

Is this your MCP?

Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find. Or connect your repo for our deepest verification, Live Monitored: read-only, revoke anytime. What we access →

⚡ Connect GitHub for Live Monitored

Install from

GitHub

M8ven verifies MCPs across every public registry — install directly from whichever one you prefer.

// key findings
✅
No credential exfiltration, no sensitive file access, no obfuscation
Static analysis found nothing flowing your secrets to unexpected places.
✅
Open source with a license and README
Anyone can audit the code, the license is declared, and the publisher documents what it does.
🔐
You'll be asked for 5 credentials: AGENTSOCIETY_LLM_API_KEY, INFINI_API_KEY, AGENTSOCIETY_CODER_LLM_API_KEY, AGENTSOCIETY_EMBEDDING_API_KEY, LITERATURE_SEARCH_API_KEY
These are read from process.env at runtime. Make sure you trust where they’ll be sent.
// environment variables
To run this server yourself, you supply these values. They go in your own MCP client configuration and stay on your machine. The secret label means the value is sensitive, not that the server mishandles it.
configCODEX_HOME
configNO_PROXY
configVIRTUAL_ENV
configno_proxy
configENABLE_DEBUGGER
configBACKEND_LOG_LEVEL
configBACKEND_HOST
configBACKEND_PORT
🔐 secretAGENTSOCIETY_LLM_API_KEY
configAGENTSOCIETY_LLM_API_BASE
configAGENTSOCIETY_LLM_MODEL
configHF_ENDPOINT
configHF_HUB_ENDPOINT
configMOBILITY_MAP_PATH
configMOBILITY_HOME_DIR
🔐 secretINFINI_API_KEY
configGRPC_VERBOSITY
configWORKSPACE_PATH
configAGENTSOCIETY_HOME_DIR
🔐 secretAGENTSOCIETY_CODER_LLM_API_KEY
configAGENTSOCIETY_CODER_LLM_API_BASE
configAGENTSOCIETY_CODER_LLM_MODEL
🔐 secretAGENTSOCIETY_EMBEDDING_API_KEY
configAGENTSOCIETY_EMBEDDING_API_BASE
configAGENTSOCIETY_EMBEDDING_DIMS
configAGENTSOCIETY_LLM_LATENCY_DEGRADE_FACTOR
configAGENTSOCIETY_LLM_SLOW_LATENCY_MS
configAGENTSOCIETY_LLM_ROUND_SAMPLE_CAP
configLITERATURE_SEARCH_MCP_URL
🔐 secretLITERATURE_SEARCH_API_KEY
configAGENTSOCIETY_LLM_REQUEST_TIMEOUT
configPYTHONPATH
configRAY_ENABLE_UV_RUN_RUNTIME_ENV
// quality suggestions

Tool annotations

No tools have read-only/destructive annotations

Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.

All four hints declared on every tool

7/7 tools missing one or more hints — tool (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); get_status (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); tool (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +4 more. OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.

For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.

Tool test coverage

Only 2/7 tools referenced in tests (29%)

Write tests that reference each tool by name so every tool has at least one test.

Shell command execution

2 calls in production code run through a shell (extension/src/services/backendManager.ts:402, extension/src/services/workspaceExportManager.ts:751)

Prefer library functions over shell-outs. If you must shell out, ensure all inputs are properly escaped.

Claim the listing to review these findings one by one and send us a correction where you disagree, straight to the team. Claiming also means we tell you when the grade moves, and reach you first if we find anything urgent.

// full audit trail
The findings above are the summary. The full trail, every check we ran, each deduction, the network hosts observed and the dependency advisories, goes to verified publishers, along with an alert whenever a new one lands. Verified publishers can also review each finding and dispute it in one click. Publisher corrections have sharpened several of our checks this month, because the maintainer knows the codebase better than any scanner.
// improvement guidance — verified publishers only
We have 4 concrete improvements we can share with the publisher of this MCP. Each comes with specific guidance to raise the trust score.
// embed badge in your README
[![M8ven Score](https://m8ven.ai/badge/mcp/tsinghua-fib-lab/agentsociety)](https://m8ven.ai/mcp/tsinghua-fib-lab/agentsociety)
Shows your grade and updates automatically. Prefer no grade? Append ?variant=verified to the badge URL.
commit: 13e28b5e67a2a8f2f43d640ebf27859126da622e
code hash: c95f0530e028d6240465917dcbc73a6a42ac7b0c3676b449adc5b8a2ec702e31
verified: 9/3/2026, 5:12:15 PM
view raw JSON →
Check MCPs from inside your assistant
Tool Check · MCP

Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.

https://m8ven.ai/api/mcp/tool-check
check_toolsearch_toolscompare_toolsrecommend_alternativescheck_publisherreport_concern
How to add it →Free · no account needed · works in any MCP client