Skip to main content
Glama

SAP MCP Server

by ai.oobeprotocol.sap.mcp

magicblock requestRandomness

magicblock_requestRandomness

Request provably fair on-chain randomness from the MagicBlock VRF oracle (Vrf1RNUjXmQGjmQrQLvJHs9SNkvDJEsRVFPkfSQUwGz). Builds an unsigned transaction that invokes request_randomness on the VRF program. Use sap_preview_transaction, sap_sign_transaction, and sap_submit_signed_transaction; do not create local signing scripts. The oracle queue defaults to the base-layer queue (Cuj97ggrhhidhbu39TijNVqE74xvKJ69gDervRUXAxGh); set ephemeral=true to use the ER queue for delegated programs. Builder fee applies.

SAP MCP execution guidance: Intent: SAP MCP tool workflow. Pricing: paid builder; estimate first, then pay/build and finalize unsigned transactions locally when returned. 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.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
payerYesWallet pubkey that will pay for the request and sign the transaction
endpointNoMagicBlock Router endpoint: 'mainnet' or 'devnet'
ephemeralNoUse the Ephemeral Rollup oracle queue instead of the base-layer queue (default false)
callerSeedYesSeed string for the VRF request — committed before randomness is produced. The seed is hashed to 32 bytes.
callbackAccountsYesAccounts to pass to the callback instruction
callbackProgramIdYesProgram ID of the callback program (the program that will consume the randomness)
callbackDiscriminatorYesBase58 or hex discriminator for the callback instruction in your program

Output Schema

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

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already indicate this is a write operation (readOnlyHint=false) and not destructive. The description adds valuable behavioral context: it builds an unsigned transaction, requires estimation, involves a paid builder, and respects signer boundaries (no keypair bytes). No contradictions with annotations.

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 reasonably well-structured with a first paragraph explaining the tool and a second paragraph for SAP MCP execution guidance. However, the second paragraph contains repetitive boilerplate that could be condensed, 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?

Given the tool's complexity (7 parameters, output schema exists), the description covers the essential context: the oracle addresses, queue options, payment and signing workflow, and output as an unsigned transaction. It is complete enough for an agent to use the tool correctly.

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 description coverage is 100%, so parameters are already well-documented. The description adds minimal extra meaning beyond the schema, such as noting that the seed is hashed to 32 bytes. This meets the baseline but does not significantly augment parameter understanding.

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?

The description clearly states the tool requests on-chain randomness from the MagicBlock VRF oracle and builds an unsigned transaction. It distinguishes itself from sibling tools like magicblock_getRandomnessResult by focusing on the request step.

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?

The description provides explicit guidance on when to use the tool, including the workflow of using sap_preview_transaction, sap_sign_transaction, and sap_submit_signed_transaction. It also instructs not to create local signing scripts and explains queue options and payment routing.

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 toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

B3.2/5.0
Disambiguation4/5

Tools are organized by protocol prefix (e.g., adrena_, jupiter_, sap_) which helps distinguish domains. Within each protocol, tool names clearly indicate actions (e.g., openPosition, getQuote). However, with 360 tools, some cross-protocol overlaps (e.g., multiple swap tools) and many similar fetch tools in the sap_* family require careful reading of descriptions to disambiguate.

Naming Consistency4/5

Each protocol group follows a consistent naming convention (e.g., snake_case for adrena_, camelCase for 3land, sap_ prefix for SAP SDK tools). The mix of conventions across protocols is acceptable, though a uniform style would improve predictability. Minor inconsistency: hyphenated names like metaplex-nft_ vs underscores.

Tool Count2/5

360 tools is far too many for a well-scoped MCP server. This aggregates dozens of protocols and SAP-specific features, making navigation difficult. The server would benefit from being split into focused micro-servers (e.g., SAP identity, Jupiter DEX, NFT tools). The current count overwhelms the coherence of the set.

Completeness4/5

The tool set covers a vast range of Solana ecosystem activities: token operations, swaps, staking, NFT management, bridging, oracle data, identity registration, chat, escrow, subscriptions, and premium streaming. Major lifecycle operations are present, though some niche subdomains may have missing functions (e.g., detailed governance or lending management). Overall, it's comprehensive for the intended scope.

Resources