Skip to main content
Glama
OOBE-PROTOCOL

SAP MCP Server

Discover SAP Agents

sap_discover_agents

Search and filter the on-chain SAP agent directory by query, wallet, protocol, capability, or x402 endpoint to discover agents for targeted interaction.

Instructions

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.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
viewNoResult shape. Use compact for broad discovery and full for detailed rows. Defaults to compact.
limitNoMaximum rows to return. Defaults to 50; hard-capped at 500.
queryNoOptional text search across name, description, agentId, wallet, PDA, x402 endpoint, protocols, capabilities, and active plugins. Example: "XONA" or "creative".
cursorNoOpaque pagination cursor returned as pagination.nextCursor by a previous sap_list_all_agents or sap_discover_agents call.
offsetNoZero-based pagination offset. Defaults to 0. Prefer cursor after the first page when nextCursor is returned.
walletNoOptional exact owner wallet public key filter. Use this when a wallet is known; it is the most reliable lookup path.
hydrateNoDeprecated compatibility alias. Use view="full" for full rows or view="compact" for directory rows.
agentPdaNoOptional exact SAP agent PDA filter.
protocolNoOptional protocol filter matched case-insensitively against agent protocols and protocol-index membership. Example: "jupiter", "creative", "payments".
capabilityNoOptional single capability ID filter matched case-insensitively. Example: "creative:imageGeneration" or "jupiter:swap".
capabilitiesNoOptional list of capability IDs. Use capabilityMode="all" when the agent must have every capability.
capabilityModeNoHow to match the capability/capabilities filters. Defaults to "any".
hasX402EndpointNoOptional filter for agents that advertise a paid HTTP/x402 endpoint.
includeInactiveNoInclude inactive agents. Defaults to false.
includeProtocolIndexesNoInclude compact protocol index summaries. Defaults to false for sap_discover_agents and true for sap_list_all_agents.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
contentYesMCP content blocks returned to the caller.
isErrorNoTrue when the tool result represents an application-level error.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed15 schema fields changedv0.9.16
    • addedInput schema / properties / agentPda
      Added value: +{
      +  "description": "Optional exact SAP agent PDA filter.",
      +  "type": "string"
      +}
    • changedInput schema / properties / capabilities / description
      Previous value: -"Array of capability IDs to filter agents by (requires at least one)"New value: +"Optional list of capability IDs. Use capabilityMode=\"all\" when the agent must have every capability."
    • changedInput schema / properties / capability / description
      Previous value: -"Single capability ID to filter agents by (e.g. \"jupiter:swap\")"New value: +"Optional single capability ID filter matched case-insensitively. Example: \"creative:imageGeneration\" or \"jupiter:swap\"."
    • addedInput schema / properties / capabilityMode
      Added value: +{
      +  "description": "How to match the capability/capabilities filters. Defaults to \"any\".",
      +  "enum": [
      +    "any",
      +    "all"
      +  ],
      +  "type": "string"
      +}
    • addedInput schema / properties / cursor
      Added value: +{
      +  "description": "Opaque pagination cursor returned as pagination.nextCursor by a previous sap_list_all_agents or sap_discover_agents call.",
      +  "type": "string"
      +}
    • addedInput schema / properties / hasX402Endpoint
      Added value: +{
      +  "description": "Optional filter for agents that advertise a paid HTTP/x402 endpoint.",
      +  "type": "boolean"
      +}
    • changedInput schema / properties / hydrate / description
      Previous value: -"Whether to include full hydrated agent profiles in results (default: true)"New value: +"Deprecated compatibility alias. Use view=\"full\" for full rows or view=\"compact\" for directory rows."
    • addedInput schema / properties / includeInactive
      Added value: +{
      +  "description": "Include inactive agents. Defaults to false.",
      +  "type": "boolean"
      +}
    • addedInput schema / properties / includeProtocolIndexes
      Added value: +{
      +  "description": "Include compact protocol index summaries. Defaults to false for sap_discover_agents and true for sap_list_all_agents.",
      +  "type": "boolean"
      +}
    • changedInput schema / properties / limit / description
      Previous value: -"Maximum number of agents to return (default: 50)"New value: +"Maximum rows to return. Defaults to 50; hard-capped at 500."
    • addedInput schema / properties / offset
      Added value: +{
      +  "description": "Zero-based pagination offset. Defaults to 0. Prefer cursor after the first page when nextCursor is returned.",
      +  "type": "number"
      +}
    • changedInput schema / properties / protocol / description
      Previous value: -"Protocol identifier to filter agents by (e.g. \"jupiter\", \"drift\")"New value: +"Optional protocol filter matched case-insensitively against agent protocols and protocol-index membership. Example: \"jupiter\", \"creative\", \"payments\"."
    • addedInput schema / properties / query
      Added value: +{
      +  "description": "Optional text search across name, description, agentId, wallet, PDA, x402 endpoint, protocols, capabilities, and active plugins. Example: \"XONA\" or \"creative\".",
      +  "type": "string"
      +}
    • addedInput schema / properties / view
      Added value: +{
      +  "description": "Result shape. Use compact for broad discovery and full for detailed rows. Defaults to compact.",
      +  "enum": [
      +    "compact",
      +    "full"
      +  ],
      +  "type": "string"
      +}
    • addedInput schema / properties / wallet
      Added value: +{
      +  "description": "Optional exact owner wallet public key filter. Use this when a wallet is known; it is the most reliable lookup path.",
      +  "type": "string"
      +}
  2. Addedv0.9.7
  3. Removedv0.9.6
  4. Changed2 schema fields changedv0.7.4
    • addedInput schema / properties / capabilities / items / description
      Added value: +"Capabilities parameter for Discover SAP Agents."
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
      +  "properties": {
      +    "content": {
      +      "description": "MCP content blocks returned to the caller.",
      +      "items": {
      +        "properties": {
      +          "text": {
      +            "description": "Human-readable JSON or text returned by the tool.",
      +            "type": "string"
      +          },
      +          "type": {
      +            "description": "MCP content block type, usually text.",
      +            "type": "string"
      +          }
      +        },
      +        "required": [
      +          "type"
      +        ],
      +        "type": "object"
      +      },
      +      "type": "array"
      +    },
      +    "isError": {
      +      "description": "True when the tool result represents an application-level error.",
      +      "type": "boolean"
      +    }
      +  },
      +  "required": [
      +    "content"
      +  ],
      +  "type": "object"
      +}
  5. Addedv0.6.0
  6. Removedv0.5.0
  7. First observedv0.1.0

TDQS

A3.5/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description claims 'Read-only SAP SDK wrapper', but annotations set readOnlyHint=false, creating a contradiction. It adds context about being a wrapper and inspecting chain state, but the contradiction undermines transparency. Also, 'Paid hosted discovery' suggests possible costs not covered by annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise with two short paragraphs. The first paragraph front-loads the core purpose and filters. The second provides contextual information. No unnecessary sentences.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the complexity (15 optional parameters, output schema exists), the description adequately covers the tool's role in the SAP ecosystem, pagination, and read-only intent. It omits details on output format, but the output schema presumably handles that.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so each parameter is already described. The description lists filter categories (query, wallet, protocol, etc.) but adds no new details beyond the schema. Baseline score of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: 'Search and filter the current on-chain AgentAccount directory' with specific filter types. It hints at sibling differentiation by mentioning 'before calling per-agent fetch tools', but does not explicitly contrast with similar tools like sap_list_all_agents.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides clear usage context: 'Use this for targeted agent discovery before calling per-agent fetch tools.' It implies alternatives (per-agent tools) but does not explicitly state when not to use this tool.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

Other Tools