MCP serverio.github.ra1labsworkx-wq/snapback

See what YOU (this agent) tend to fail on — your recurring failure patterns across past diagnoses. Returns your top failure classes with counts and what share of your failures each

Live MID-RUN budget check (fast, no LLM). Send whatever counters you have and get an advisory on context %, token burn, cost burn, step budget, and off-task drift - with concrete s

Given an ORDERED list of errors from a run (oldest first), find the TRUE root — the error that cascaded or shouldn't have been retried — not just the final symptom you see. E.g. a

Turn your raw logs into a Snapback trace so you don't hand-craft JSON. Pass 'source' = a list of log/step entries, or an object with a spans/steps/messages/events/logs array (OTel

MID-RUN loop check (fast, no LLM, free). Send your recent steps DURING a run; get back whether you're stuck repeating a tool call and a concrete next move. Call this every few step

Diagnose SEVERAL traces in one call (up to 20). Each trace is metered like a separate diagnose_trace. Returns a verdicts array (per-trace, order preserved); a bad trace in the batc

Diagnose a cryptic AGENT-INFRASTRUCTURE error — payments (x402/EIP-3009), Solana on-chain (ATA, blockhash, compute), MCP protocol, RPC/providers, EVM & Solana wallets, library of V

Diagnose why an AI agent run failed. Returns a structured verdict (failure_class, failed_at_step, root_cause, fix_suggestion, confidence). LATENCY: known patterns return library-in

Check what happened to a pattern you requested (from request_pattern's request_id). Returns pending / approved / rejected / in_library so you can see if your suggestion was actione

Fetch a previously produced verdict by its id or by trace_id (your org only).

See how your feedback + pattern requests have shaped the shared library — how many verdicts you've rated, patterns you've requested, and how many were approved into the library. Tu

See YOUR current usage + remaining allowance so you can self-govern spend: snapbacks (diagnoses) used/cap/remaining, guard checks used/cap/remaining, estimated spend, % used, and w

BEFORE running: get known failure patterns for a given agent setup so you can avoid them. Returns a ranked list of {failure_class, root_cause, fix_suggestion} from Snapback's libra

Should you RETRY the same target, SWITCH provider, FALL BACK to another chain, or STOP? Pass the error + your configured topology (current_chain, available_chains, and/or current_p

Report the outcome of an auto-applied fix (the self-heal interceptor calls this after it gate-applied a fix and retried). Pass failure_class, family, fix, confidence, action_class,

Leave us a message: ask us to add a failure pattern to the library, or report a problem we couldn't diagnose well. Use this when diagnose_trace didn't have a good answer, when you

Search Snapback's documentation for how to use it — how to format a trace, what each tool does, the failure taxonomy, auth, pricing, and errors. Free and needs no token. Call this

Close a live session and get a short run summary (total steps, duration). Frees the session. Free, no token.

Open a LIVE mid-run session so Snapback can watch your run step-by-step and warn you in real time (loop / token / cost / context) - the always-on guardian mode. Returns a session_i

Report ONE step of a live run and get back any warnings immediately (loop detected / budget breach). Pass the step (action + inputs) and any counters you have (step, max_steps, tok

Tell Snapback whether a verdict was correct (correct=true/false), with an optional free-text note (did the fix work? what was wrong?). ONE rating per verdict — call it AFTER you ac

Approaching a token/context/cost budget mid-run? Pass your counters and get the LEAST-DISRUPTIVE recovery ranked: truncate context | switch to a cheaper model | batch steps | wrap

THE CROWD: for a failure_class (or pass the family/error and we'll map it), see what OTHER agents did about the same failure and whether it worked — anonymized, aggregated across e