polygraph.so
Login

Virtuals-Protocol MCP index

Independent, reproducible behavioral grades for the MCP surface of the Virtuals ecosystem — the protocol’s own commerce and framework infrastructure, and the agents and apps launched on it.

1A1B1D· 3 graded · 2 pending · 16 no MCP
Virtuals launches agents permissionlessly — the protocol doesn’t vet how any of them behave. This is that vetting, applied to the ecosystem’s MCP surface.
Each server is graded on its own MCP surface. Most agents launch via GAME/ACP rather than a bespoke server, so they carry no standalone MCPto grade — mapped honestly below. Grades reflect the testable surface (state-changing tools aren’t exercised by default); remote-only servers cap at B (egress unverifiable), npm servers run sandboxed and can reach A, and a C-04 (adversarial-input) failure caps a grade at D. 3rd-partymarks a community wrapper rather than the project’s own server. These rows are not published — no public badge or report shows them.
B
agent-to-agent commerce gateway
C-01 passC-02 skipC-03 pass
agent framework
the agent framework/SDK (@virtuals-protocol/game) — build tool, not an MCP server
no standalone MCP
A
ACP Find2026-07-04
ACP marketplace search · 3rd-party
C-01 passC-02 passC-03 pass
D
invinoveritas2026-07-05
agent verification oracle · 3rd-party
C-01 passC-02 failC-03 pass
·
Maiat Protocol
agent trust oracle · 3rd-party
grade pending · non-standard
·
web3agent
wallet agent w/ ACP toolset · 3rd-party
grade pending · api-key
social + on-chain analytics
HTTP API + extension, no MCP
no standalone MCP
crypto-market intelligence
flagship market-intel agent — no public MCP
no standalone MCP
AI / DeSci VC agent
$AIXCB
no standalone MCP
AI hedge-fund agent
names MCP internally; no connectable endpoint
no standalone MCP
Convo Agent
conversational agent
Prefrontal Cortex conversational agent
no standalone MCP
DeFi trading automation
highest-volume ACP agent; via ACP not MCP
no standalone MCP
Fabric Protocol
agent infrastructure
agent infra ($ROBO)
no standalone MCP
entertainment / VTuber agent
autonomous entertainment agent
no standalone MCP
Mamo
DeFi assistant (Base)
DeFi assistant agent
no standalone MCP
prediction-markets trading
via Polymarket API
no standalone MCP
Ribbita
community / meme agent
community agent ($TIBBIR)
no standalone MCP
AI investment / VC agent
$SEKOIA
no standalone MCP
AI-agent DAO / investing
agent-run investment DAO
no standalone MCP
VPay
agent payments
agent payments
no standalone MCP
omnichain agent protocol
proprietary Paths/Shells, not MCP
no standalone MCP

Monitor the Virtuals agent ecosystem.

This index is a snapshot. As agents launch on Virtuals, we re-grade the ecosystem's MCP surface on a cadence and flag regressions — a dropped grade, a newly failing probe, a changed tool surface — before they reach your users. Set up per ecosystem.

Prefer to write us directly? hello@polygraph.so

C-01 tool-output injection · C-02 permission/egress overreach · C-03 sensitive-data handling · C-04 adversarial input (off-table; caps the letter at D). Adoption is reach (0–100), not safety — the grade is the verdict. Reproduce any grade by re-running the open harness against the same ref. Each server links to its polygraph report; see the full MCP Security Index.