Sourcey
OfficialServer Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| SOURCEY_MCP_URL | No | Select another HTTPS Sourcey endpoint. Plain HTTP is accepted only for a loopback test server. URLs containing credentials or fragments are refused. | https://mcp.sourcey.com/mcp |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| search_offersA | Search current startup credits and deals, including cloud credits, SaaS discounts, free tiers, grants, perks, and partner offers. Filter by query, vendor, or category and evaluate eligibility from typed company facts; unknowns remain explicit. |
| compare_offersA | Compare two to ten startup credit or deal offers side by side, including value, access requirements, eligibility, freshness, and evidence. Unknown eligibility and unsupported stacking remain explicit. |
| inspect_evidenceA | Inspect the provenance behind startup credits and deals. Resolve one to ten exact revisions to supporting events and observations, including freshness and dispute status. |
| get_changesA | Track added, changed, withdrawn, and removed startup credits, discounts, free tiers, perks, and deals through Sourcey's signed change feed after an optional cursor. |
| search_readinessA | Search published Agent Readiness report cards for APIs, SaaS products, authentication, payments, provisioning, operations, and recovery. Returns the overall A+ to F grade, five-stage outcomes, evidence coverage, freshness, primary blocker, remediation context, and canonical report URL without conflating service readiness with startup-credit eligibility. |
| get_readinessB | Get one exact published Agent Readiness report card with its visible A+ to F grade, five service-use stages, individual findings, blockers, remediations, tested surfaces, methods, evidence state, coverage, freshness, policy identity, provenance, and canonical URL. Resolve by immutable profile ID or by one Entity plus exact product and funnel. |
| prepare_declarationB | Prepare the canonical declaration for an independent Agent Readiness assessment of one vendor product, API, SaaS service, authentication path, payment path, provisioning flow, operating interface, recovery flow, and exact agent standard, ready to submit through POST /v1/submissions as product agent_readiness. Resolves only exact Sourcey Entity identity, never assigns a grade or treats startup credits and deals as service readiness, and returns precise missing fields when the service graph is incomplete. |
| get_servicesA | Discover Sourcey's enabled paid agent services and canonical HTTP resources, including exact request and response contracts, price floor, policy links, and x402 discovery. Payment and durable job status remain on the product HTTP API; this read-only MCP tool never signs, settles, or interprets a payment. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 8 tools
The set splits into two clear domains (startup offers vs. Agent Readiness) with search/get/compare/inspect patterns that read as distinct actions. Within each domain the verbs are reasonably unambiguous, though the verbose, jargon-heavy descriptions for prepare_declaration, search_readiness, and search_offers create some risk of overlap confusion around eligibility vs. readiness.
All eight tools use a consistent snake_case verb_noun pattern (compare_offers, search_offers, get_readiness, get_services, etc.). Verb choices map predictably to intent (search_ for collections, get_ for a single exact record, prepare_ for submissions). No camelCase or stylistic mixing.
Eight tools is well-scoped for a read-mostly discovery/assessment server. Two coherent sub-domains (offers and readiness) are each covered with a small, focused tool set plus one meta-discovery tool, with no redundant entries.
The surface covers search, comparison, change tracking, provenance inspection, and single-record retrieval across both domains, plus service discovery and a submission-preparation path. Minor gaps remain, e.g. no dedicated get_offer for a single offer and no explicit listing of entities/subjects, though agents can work around via search.