SAP MCP Server

Start SAP MCP Agent Mode

sap_agent_start

Read-onlyIdempotent

Return the concise startup playbook for agents using SAP MCP. Call this when the user says "Start SAP MCP", "Initialize SAP MCP", "Load SAP", or asks what SAP MCP can do.

SAP MCP execution guidance: Intent: agent bootstrap, routing, skills, or repair guidance. Pricing: free; call directly without x402. Routing: free hosted call; call directly and keep it small/exact when possible. Signer boundary: hosted reads/builders never receive keypair bytes; value-moving results must be finalized locally when signing is required.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`goal`	No	Optional user goal to tailor the startup plan, such as "register an agent", "check wallet balance", or "swap tokens".

Output Schema

TableJSON Schema

Name	Required	Description
`success`	Yes	Whether the bootstrap instructions were generated.
`serverMode`	Yes	Current SAP MCP server mode.
`paymentFlow`	Yes	How to handle hosted x402/pay.sh paid calls safely.
`repairCommand`	Yes	Wizard command to repair local hosted/profile/payment bridge setup.
`hostedEndpoint`	Yes	Canonical hosted SAP MCP endpoint.
`connectionCheck`	Yes	How agents should answer simple connection/status questions.
`activationPhrases`	Yes	Short user phrases that should trigger this bootstrap behavior.
`userFacingSummary`	Yes	Short text the agent can show the user after startup.
`immediateToolCalls`	Yes	Tool calls the agent should run first when available.
`sessionContextPacket`	Yes	Machine-readable SAP MCP routing, freshness, memory, proof-tape, and forbidden-action rules for this session.

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedJul 26, 2026

addedOutput schema / properties / sessionContextPacket

Added value: +{
+  "description": "Machine-readable SAP MCP routing, freshness, memory, proof-tape, and forbidden-action rules for this session.",
+  "type": "object"
+}

changedOutput schema / required

Previous value: -[
-  "success",
-  "activationPhrases",
-  "hostedEndpoint",
-  "serverMode",
-  "immediateToolCalls",
-  "paymentFlow",
-  "connectionCheck",
-  "userFacingSummary",
-  "repairCommand"
-]New value: +[
+  "success",
+  "activationPhrases",
+  "hostedEndpoint",
+  "serverMode",
+  "immediateToolCalls",
+  "paymentFlow",
+  "sessionContextPacket",
+  "connectionCheck",
+  "userFacingSummary",
+  "repairCommand"
+]

Changed1 schema field changedJul 24, 2026

addedInput schema / description

Added value: +"Start SAP MCP Agent Mode input schema. Intent: agent bootstrap, routing, skills, or repair guidance. Pricing: free; call directly without x402. Routing: free hosted call; call directly and keep it small/exact when possible. Signer boundary: hosted reads/builders never receive keypair bytes; value-moving results must be finalized locally when signing is required. Use exact field names from this schema; do not guess aliases or include private key material."

AddedJul 17, 2026

TDQS

A4.2/5.0

Behavior4/5

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, so the tool is safe. Description adds valuable context on costing (free, no x402), routing (keep small/exact), and signer boundary (no keypair bytes on hosted side), which are beyond what annotations provide.

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

Conciseness3/5

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

The description is front-loaded with the main purpose in the first sentence. However, the second paragraph repeats text from the input schema description (pricing, routing, signer boundary), making it less concise than ideal.

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?

With an output schema present and annotations covering safety, the description covers usage and behavioral traits well. It lacks detail on what the 'startup playbook' actually contains (e.g., format or structure), but the output schema likely fills this gap.

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% for the single 'goal' parameter, and its description is clear. The tool description does not add significant new information beyond what's in the schema, so baseline 3 is appropriate.

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

Purpose5/5

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

Description explicitly states it returns a startup playbook for agents using SAP MCP. It distinguishes itself by focusing on bootstrapping and guidance, contrasting with sibling tools that perform specific actions like trading or staking.

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

Usage Guidelines5/5

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

Description provides clear invocation triggers: when user says 'Start SAP MCP', 'Initialize SAP MCP', 'Load SAP', or asks about capabilities. It also includes execution guidance on pricing, routing, and signer boundary, making it a complete usage guide.

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

All SAP MCP Server tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.