MISSING
https://missing-production-e3da.up.railway.app/mcp ↗
Description
Fallback capability resolver for AI agents with replay-verified discovery and x402 paid execution.
What our measurements say
MISSING is a remote MCP server published at missing-production-e3da.up.railway.app. It has been probed 6 times since 9/12/2026. It answered in 6 of them (100.0%), a near-uninterrupted record. Median response time is 577 ms, a delay an agent will notice. It offers a narrow, focused set of 4 tools. On the protocol side it speaks the 2026-07-28 stateless spec.
Agent readability score
Can an LLM agent pick the right tool here — names, descriptions and parameter clarity are assessed.
Agent readability score
Strengths
- list_verified_capabilities and search_verified_capabilities have distinct, actionable purposes
- resolve_capability uses precise parameter naming (capability, input)
Weaknesses
- Multiple tool descriptions are truncated mid-sentence
- record_missing_capability_demand's name is overly verbose and ambiguous
- Parameter types like 'object' lack schema specificity
list_verified_capabilities— Description cuts off mid-sentence without explaining payment implicationssearch_verified_capabilities— Truncated description hides critical execution limitationsrecord_missing_capability_demand— Ambiguous name with unclear demand prioritization mechanismresolve_capability— Incomplete explanation of payment_required workflow
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 not run this round
- Cold-start: cold 179ms → warm 178ms (penalty 1ms)
Tools
Tools the server advertised in the latest measurement — measured, not catalog-claimed.
list_verified_capabilitiesList every replay-verified capability currently executable by MISSING. Use this to inspect the catalog, obtain exact capability identifiers, or copy example inputs before resolve_capability; for fuzzy natural-language intent, use search_verified_capabilities instead. This is read-only, has no payment or provider side effect, and returns capability, family, provider, and example_input metadata.
search_verified_capabilitiesSearch the replay-verified MISSING catalog from a natural-language task description. Use this when you know the task you want performed but not the exact capability identifier; if a match is suitable, pass its capability and a valid input object to resolve_capability. This is read-only: it does not call providers, create demand, or trigger payment; limit defaults to 5 and only controls the maximum number of matches.
querystringrequiredlimitinteger
record_missing_capability_demandRecord a capability need that MISSING cannot currently resolve so the trusted acquisition system can prioritize new supply. Call this only after list/search finds no suitable verified capability; it mutates the durable demand ledger and repeated calls may increase the observed demand signal. The mutation is additive and non-destructive; never put secrets, credentials, personal data, payment material, or private keys in intent or example_input.
intentstringrequiredcapabilitystringexample_inputobject
resolve_capabilityPrepare paid execution of one exact replay-verified capability. Use this only after you have an exact capability identifier, normally from list_verified_capabilities or search_verified_capabilities; this MCP call itself does not execute a provider or charge the caller, but returns payment_required with the canonical /v1/agent/resolve endpoint, current price, exact request body, and x402 instructions. The later HTTP x402 flow performs execution and settlement: preserve the exact request body and exact PAYMENT-SIGNATURE for recovery, and do not create a second authorization for a payment already associated with a known transaction.
capabilitystringrequiredinputobjectrequired
Availability history
Event log
Derived by comparing consecutive probes — changes in era, protocol version, build and reachability.
- Added to watch — era: Dual-era
Get your badge
Add this badge to your README — it updates automatically as measurements change.
[](https://mcpmetrics.io/servers/io-github-leoleon506-missing)<a href="https://mcpmetrics.io/servers/io-github-leoleon506-missing"><img src="https://mcpmetrics.io/badge/io.github.leoleon506/missing/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.
- mcp-x402 — MCP server for agents with autonomous USDC/RLUSD paymentsmcp-x402.onrender.com
85+ pay-per-call MCP tools: trading, federal grants/contracts, SEC, FTD. x402 USDC/RLUSD. No keys.
- AI Orderability (AIO) Agents CPG with x402: Retail & Marketplace Sourcingmcp.gsc-marketplace.ai
CPG sourcing for AI Agents with x402: BPC brands, agent IM, Trading Desk. GreenCore Solutions Corp.
- x402 Discovery MCPx402-scout-relay.onrender.com
Discover x402 APIs by capability, price & trust. Powered by x402Scout.
- SparkForge — 20+ Utility APIs with x402 Micropaymentssparkforge.sh
20+ pay-per-use APIs: image gen, crypto data, email verify, SSL check, web scraping, and more.
- Learn with Agentslearnwithagents.app
Your AI agent builds interactive block-based courses over MCP; take them at learnwithagents.app.
- x402-seller — rug protection & safe-alpha for trading agentsx402-seller-m8nx.onrender.com
Rug-check & launch radar for trading agents: composite honeypot score, EVM+Solana, keyless x402.
Comments
Sign in to write a comment
No comments yet. Be the first.