Use the SAP MCP Wizard or install the library from the npm registry to automatically create and configure a Solana/SAP wallet via https://mcp.sap.oobeprotocol.ai
- capability exposure inferred + 35
- recent drift inferred + 20
- tool safety inferred + 25
- trust mitigators mixed − 8
inferred mixed
The A–E grade is our heuristic synthesis — a "review this" prompt, not a verdict. Each factor is tagged by what backs it: attested (a verifiable record), reported (a third party's claim), or inferred (our own heuristic, e.g. permissions). See methodology.
graded 5m ago · see ecosystem CVEs →
- D · 64 → D · 72
- C · 39 → D · 64
No known CVEs for this server.
- high dangerous code
credential logged in 1 file(s)
- high exfiltration combo sap_discover_agents
single tool reads + sends: fs, net, db
- medium exfiltration combo blinks_validateActionsJson
single tool reads + sends: fs, net
- medium purpose mismatch sap_runtime_repair_plan
benign-looking name carries shell
- medium tool poisoning sap_discover_agents
cross-tool-steering: "before calling"
- medium toxic flow (lethal trifecta)
lethal trifecta reachable across this server's tools: private-data access + untrusted-content ingestion + network exfil
- low dangerous code
env-secret-flows-to-network-js: A process environment value (often a secret/token) flows into a network call — possible credential exfiltration. (OOBE-PROTOCOL-sap-mcp-11f90f4/src/
analyzed commit 11f90f4 · analyzer v28 · 4d ago
skills & prompt files 20
- skill OOBE-PROTOCOL-sap-mcp-11f90f4/skills/sap-agent-chat/SKILL.md
- skill OOBE-PROTOCOL-sap-mcp-11f90f4/skills/sap-agent-registry/SKILL.md
- skill OOBE-PROTOCOL-sap-mcp-11f90f4/skills/sap-agentkit/SKILL.md
- skill OOBE-PROTOCOL-sap-mcp-11f90f4/skills/sap-clawpump-bridge/SKILL.md
- skill OOBE-PROTOCOL-sap-mcp-11f90f4/skills/sap-defi/SKILL.md
- skill OOBE-PROTOCOL-sap-mcp-11f90f4/skills/sap-discovery-indexing/SKILL.md
- skill OOBE-PROTOCOL-sap-mcp-11f90f4/skills/sap-escrow-settlement/SKILL.md
- skill OOBE-PROTOCOL-sap-mcp-11f90f4/skills/sap-ledger-session/SKILL.md
- skill OOBE-PROTOCOL-sap-mcp-11f90f4/skills/sap-market-data/SKILL.md
- skill OOBE-PROTOCOL-sap-mcp-11f90f4/skills/sap-mcp/SKILL.md
- skill OOBE-PROTOCOL-sap-mcp-11f90f4/skills/sap-memory-vault/SKILL.md
- skill OOBE-PROTOCOL-sap-mcp-11f90f4/skills/sap-nft-metaplex/SKILL.md
- skill OOBE-PROTOCOL-sap-mcp-11f90f4/skills/sap-operations/SKILL.md
- skill OOBE-PROTOCOL-sap-mcp-11f90f4/skills/sap-payments-x402/SKILL.md
- skill OOBE-PROTOCOL-sap-mcp-11f90f4/skills/sap-reputation-attestation/SKILL.md
- skill OOBE-PROTOCOL-sap-mcp-11f90f4/skills/sap-sns/SKILL.md
- skill OOBE-PROTOCOL-sap-mcp-11f90f4/skills/sap-social-gaming/SKILL.md
- skill OOBE-PROTOCOL-sap-mcp-11f90f4/skills/sap-solana-token/SKILL.md
- skill OOBE-PROTOCOL-sap-mcp-11f90f4/skills/sap-staking/SKILL.md
- skill OOBE-PROTOCOL-sap-mcp-11f90f4/skills/sap-tool-registry/SKILL.md
danger signals1
- credential in logs credential in log OOBE-PROTOCOL-sap-mcp-11f90f4/src/signer/load-keypair.ts :63
logger.debug('Loaded keypair from environment', { envVar, publicKey: Keypair.fromSecretKey(secretKey).publicKey.toBase58() });
- recent drift +20 capability drift →
[](https://mcpobservatory.com/servers/github:OOBE-PROTOCOL/sap-mcp/security) Heuristic, inferred signals — false positives (legitimately powerful tools, forks, language ports) are expected. Treat each as "review this", not a verdict. See the ecosystem-wide picture on the security hub, or the fleet security of oobe-protocol.