Axiom Relay
https://axiomrelay.io/mcp/discovery ↗
Description
Free agent-service discovery, OpenAPI document checks, and receipt verification. No API key needed.
What our measurements say
Axiom Relay is a remote MCP server published at axiomrelay.io. It has been probed 8 times since 9/12/2026. It answered in 8 of them (100.0%), a near-uninterrupted record. Median response time is 921 ms, a delay an agent will notice. It offers a narrow, focused set of 10 tools. On the protocol side it still runs 2025-11-25 and has not moved to the newer spec.
Agent readability score
Can an LLM agent pick the right tool here — names, descriptions and parameter clarity are assessed.
Agent readability score
Strengths
- Tool names clearly indicate their primary function (e.g., 'verify_receipt', 'compareServices')
- Risk levels (R0-R2) and public access without API keys are explicitly documented
- Comprehensive parameter lists with required/optional flags
Weaknesses
- Some tool names are too similar (e.g., 'get_axiom_capabilities' vs 'get_axiom_capability')
- Parameter types like 'object' and 'array' lack structural definitions
- Overlapping functionality between 'search_directory' and 'find_paid_service'
- No explicit error handling or constraint documentation
get_axiom_capabilities— Similar name to 'get_axiom_capability' causes potential confusionsearch_directory— Excessive parameters without clear use-case boundariesfind_paid_service— Overlaps with 'search_directory' in service discovery functionalitymaxCandidatePrice— Object type parameter lacks structural definition in 'find_paid_service'axiom_api_doctor— No documentation of API specification format requirements
Verdict
Event narrative
Risk: low
Advice
Schema compliance
tools/list structure, inputSchema validity, and a functional smoke test — the components of the 0-100 score.
- tools/list schema valid
- inputSchema is valid JSON Schema
- Smoke test passed · last run:
- Cold-start: cold 175ms → warm 178ms (penalty 0ms)
Tools
Tools the server advertised in the latest measurement — measured, not catalog-claimed.
get_axiom_capabilitiesList the canonical, versioned capabilities approved for public discovery. No commercial obligation. Risk R0; PUBLIC.
kindstringriskClassstring
get_axiom_capabilityRead one canonical capability contract by stable identifier. No commercial obligation. Risk R0; PUBLIC.
idstringrequired
search_directoryList neutral directory entries projected from CapabilityContract and Merchant records with explicit filters and ranking policy. No commercial obligation. Risk R0; PUBLIC.
querystringcapabilitystringcategorystringmerchantTypestringminPricestringmaxPricestringdenominationstringsettlementProfilestringtierstringstatusstringprotocolstringreceiptProfilestringauthorizationstringrankingClassstringthirdPartyOnlyboolean
get_directory_entryRead one canonical directory entry by slug, capability id, or stable directory id. No commercial obligation. Risk R0; PUBLIC.
entrystringrequired
find_paid_serviceSearch public service contracts by declared text and optional price ceiling without an opaque ranking score. No commercial obligation. Risk R0; PUBLIC.
querystringrequiredmaxCandidatePriceobject
compareServicesCompare two to four declared service contracts field by field without creating a ranking score. No commercial obligation. Risk R0; PUBLIC.
slugsarrayrequired
listRoomsList truthful room contracts, participation policy, and transport availability. No commercial obligation. Risk R0; PUBLIC.
verify_receiptValidate the public MER envelope, canonical evidence links, and sandbox Ed25519 proof without trusting marketplace claims. No commercial obligation. Risk R1; PUBLIC.
axiom_concierge_answerAxiom Concierge Core performs bounded first-agent work through the shared capability policy dispatcher. No commercial obligation. Risk R1; PUBLIC.
questionstringrequired
axiom_api_doctorAPI Doctor performs bounded first-agent work through the shared capability policy dispatcher. No commercial obligation. Risk R2; PUBLIC.
apiDescriptionobjectrequired
Availability history
Event log
Derived by comparing consecutive probes — changes in era, protocol version, build and reachability.
- Added to watch — era: Legacy
Get your badge
Add this badge to your README — it updates automatically as measurements change.
[](https://mcpmetrics.io/servers/io-github-itr3k-axiom-relay-discovery)<a href="https://mcpmetrics.io/servers/io-github-itr3k-axiom-relay-discovery"><img src="https://mcpmetrics.io/badge/io.github.Itr3k/axiom-relay-discovery/era.svg" alt="mcpmetrics"></a>You are seeing the last 7 days. Sign up for the full history. Which check failed and why is in the dashboard.
Sign up free to seeSimilar MCP servers
The catalog entries whose name and description are closest to this one, found with the same index the search box uses.
- Ardaro Agent Utilities & Document Checksagents.getardaro.com
Receipt 0.25; invoice 0.50; advisory context 0.05, intent 0.15, budget 0.10, ledger 0.25 USDC.
- Agent Discovery Doctor - llms.txt, agent card, mcp.jsonwww.pathwren.workers.dev
{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"whoami","arguments":{}}} free no key
- Agent Relayagent.qtrade.top
Agent Relay 是一个开源的 Agent 协作中继。两个在不同电脑上的 AI Agent 通过邀请码建立频道，实时互通消息、发布结构化 Agent 合约，遇到越权或无法决定的事停下来，让各自的人类审批，不再需要人肉复制粘贴消息。 支持 Claude Code、Cursor、Codex、Kimi、WorkBuddy 等 MCP 客户端，也提供单文件 CLI。开源、可自托管、MIT License。
- Meyhem — MCP Server Discovery & Agent Searchapi.rhdxm.com
Discover 6,700+ MCP servers and 15,000+ OpenClaw skills. Agent-native search with outcome ranking.
- AIﾉアカリ☆ Agent Trust Receiptai-akari.ai
Read-only Remote MCP for externally grounded AI agent trust receipts.
- Bench Agent Discoverybench.virajmishratakehome.workers.dev
Discover public AI agents, reusable recipes, and trusted benchmark evidence by task.
Comments
Sign in to write a comment
No comments yet. Be the first.