sap_discover_agents
Paid hosted discovery for SAP agents. Search and filter the current on-chain AgentAccount directory by query, wallet, protocol, capability, x402 endpoint presence, and cursor pagination. Use this for targeted agent discovery before calling per-agent fetch tools. SAP MCP context: Read-only SAP SDK...
This record as markdown: /tools/oobe-protocol-labs-sap-mcp-server/sap-discover-agents.md
What sap_discover_agents does on Sap
AI agents call sap_discover_agents to retrieve information from Sap without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
view | string | — | Result shape. Use compact for broad discovery and full for detailed rows. Defaults to compact. |
limit | number | — | Maximum rows to return. Defaults to 50; hard-capped at 500. |
query | string | — | Optional text search across name, description, agentId, wallet, PDA, x402 endpoint, protocols, capabilities, and active plugins. Example: "XONA" or "creative". |
cursor | string | — | Opaque pagination cursor returned as pagination.nextCursor by a previous sap_list_all_agents or sap_discover_agents call. |
offset | number | — | Zero-based pagination offset. Defaults to 0. Prefer cursor after the first page when nextCursor is returned. |
wallet | string | — | Optional exact owner wallet public key filter. Use this when a wallet is known; it is the most reliable lookup path. |
hydrate | boolean | — | Deprecated compatibility alias. Use view="full" for full rows or view="compact" for directory rows. |
agentPda | string | — | Optional exact SAP agent PDA filter. |
protocol | string | — | Optional protocol filter matched case-insensitively against agent protocols and protocol-index membership. Example: "jupiter", "creative", "payments". |
capability | string | — | Optional single capability ID filter matched case-insensitively. Example: "creative:imageGeneration" or "jupiter:swap". |
capabilities | array | — | Optional list of capability IDs. Use capabilityMode="all" when the agent must have every capability. |
capabilityMode | string | — | How to match the capability/capabilities filters. Defaults to "any". |
Parameters from the server's own tool schema.
Why sap_discover_agents is rated Low
Tool queries blockchain state for discovery without modifying data or executing operations.
From the tool's definition Search and filter the current on-chain AgentAccount directory; read-only SAP SDK wrapper
Risk signalsHigh parameter count (15 properties)
Attacks that exploit this kind of access
The rule that runs sap_discover_agents safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Sap, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For sap_discover_agents, this is the rule to start with:
sap_discover_agents is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Sap, apply this rule, and every sap_discover_agents call is checked against it from then on.
Questions about sap_discover_agents
Paid hosted discovery for SAP agents. Search and filter the current on-chain AgentAccount directory by query, wallet, protocol, capability, x402 endpoint presence, and cursor pagination. Use this for targeted agent discovery before calling per-agent fetch tools. SAP MCP context: Read-only SAP SDK wrapper against the configured Solana RPC and SAP program. Use these reads to inspect current chain state before mutating registry, payment, reputation, memory, or tool accounts. SAP MCP execution guidance: Intent: read/discovery workflow. Pricing: paid read-premium; estimate first, then use sap_payments_call_paid_tool when the runtime cannot replay x402 natively. Routing: paid hosted call; call sap_estimate_tool_cost first, then use sap_payments_call_paid_tool if the runtime cannot handle x402 natively. Signer boundary: hosted reads/builders never receive keypair bytes; value-moving results must be finalized locally when signing is required. It is categorised as a Read tool in the Sap MCP Server, which means it retrieves data without modifying state.
sap_discover_agents accepts 12 parameters: view, limit, query, cursor, offset, wallet, hydrate, agentPda, protocol, capability, capabilities, capabilityMode. The full parameter table on this page comes from the server's own tool schema.
Register the Sap MCP server in PolicyLayer and add a rule for sap_discover_agents: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Sap. Nothing to install.
sap_discover_agents is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the sap_discover_agents rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for sap_discover_agents. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
sap_discover_agents is provided by the Sap MCP server (https://mcp.sap.oobeprotocol.ai/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Sap, and thousands of servers like it.
This server
Across the catalogue