MCP server

Snapback

io.github.ra1labsworkx-wq/snapback

Checked 26 Oct 2026, 08:29 UTC · Connected to it and listed its tools

Diagnose why an AI agent failed and get the verified fix instantly. Free, no token.

Source

At a glance

Type

MCP server

Publisher

Not verified

Status

Working at last check

Tools

23

Token cost

About 4,527 tokens per request

Sets up in

Claude Code, Claude Desktop, Codex, Gemini CLI, Cursor, VS Code, Antigravity, ChatGPT, OpenAI API, Grok

Last checked

26 Oct 2026, 08:29 UTC

Connect it to your agent

Add to CursorAdd to VS CodeVS Code Insiders

Opens the app, which shows the server and asks you to confirm. For other apps, copy the setup below.

Claude Code

claude mcp add --transport http snapback https://api.snapback.sh/mcp

Claude Desktop

Settings → Connectors → Add custom connector, and paste the URL.

Codex (config.toml)

[mcp_servers.snapback]
url = "https://api.snapback.sh/mcp"

Gemini CLI

{"mcpServers":{"snapback":{"httpUrl":"https://api.snapback.sh/mcp"}}}

Cursor

{"mcpServers":{"snapback":{"url":"https://api.snapback.sh/mcp"}}}

VS Code

{"servers":{"snapback":{"type":"http","url":"https://api.snapback.sh/mcp"}}}

Antigravity

agy mcp add snapback https://api.snapback.sh/mcp

ChatGPT

Settings → Apps & Connectors → Advanced settings: turn on Developer mode, then Create a connector and paste the URL. Which plans can do this varies.

OpenAI API (Responses tools)

{"type":"mcp","server_label":"snapback","server_url":"https://api.snapback.sh/mcp","require_approval":"always"}

Grok (xAI API tools)

{"type":"mcp","server_label":"snapback","server_url":"https://api.snapback.sh/mcp"}

Tools

• agent_memory ~142 tokens
  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 is (e.g. 'loop_repeated_tool_call: 12 times, 40%'). Call it before a run to know what to guard against. Token-scoped to
• budget_guard ~307 tokens
  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 suggested_actions and the projected cost of NOT acting. Call it every few steps to catch a runaway BEFORE you hit a limit
• cascade_root ~167 tokens
  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 429 that got retried and triggered a downstream 401: the root is the 429, not the 401. Each error can be a string or {er
• convert_trace ~184 tokens
  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 spans, OpenAI/LangChain message lists, or generic {tool,input,output} arrays all work). Returns {trace} ready to pass st
• detect_loop ~191 tokens
  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 steps to catch a loop BEFORE you burn your step budget — don't wait for a postmortem. Non-blocking advice, not a verdict.
• diagnose_batch ~138 tokens
  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 batch is isolated and doesn't fail the rest. Use for post-run analysis of many failures at once instead of N round-trips.
• diagnose_infra_error ~451 tokens
  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 VERIFIED fixes the base model often gets wrong. Pass the error text (and optional context). Returns {matched, family, fai
• diagnose_trace ~152 tokens
  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-instant (<1s); a NOVEL failure needs an LLM call and can take up to ~25s — set your client timeout to at least 30s, and tr
• get_request_status ~111 tokens
  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 actioned — the feedback loop isn't a black box. Free, no token.
• get_verdict ~68 tokens
  Fetch a previously produced verdict by its id or by trace_id (your org only).
• my_impact ~98 tokens
  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. Turns your input into visible collaboration. Token-scoped to you.
• my_usage ~102 tokens
  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 when it resets. Call it periodically to avoid surprises. Token-scoped, free.
• preflight ~173 tokens
  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 library. Call this before executing a plan and self-correct.
• recommend_failover ~292 tokens
  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_provider, available_providers) and get deterministic routing advice with the reason — so a flaky Solana RPC doesn't get r
• report_outcome ~316 tokens
  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, and succeeded (did the retry work?). TWO purposes: it's your safety telemetry (spot a fix that didn't work) AND it feed
• request_pattern ~251 tokens
  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 keep hitting a failure we don't classify, or when you want a specific kind of problem supported. It goes straight to our
• search_docs ~152 tokens
  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 first if you're unsure how to format a request or what a verdict means.
• session_end ~72 tokens
  Close a live session and get a short run summary (total steps, duration). Frees the session. Free, no token.
• session_start ~124 tokens
  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_id. Free, no token. Call session_step as you run, session_end when done.
• session_step ~226 tokens
  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, tokens_used, token_budget, cost_used_usd, cost_budget_usd, context_used, context_window, task, recent_actions. context_wind
• submit_feedback ~275 tokens
  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 act on a verdict and see the outcome. Your correction updates the SHARED pattern library (fix patterns are shared anonymiz
• suggest_budget_recovery ~202 tokens
  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 up — scored by speed gained, accuracy lost, cost saved. Turns budget_guard's 'you're at 94%' into 'here's what to do abo
• what_others_did ~333 tokens
  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 everyone. Returns {total, agree_pct (community success rate), distinct_orgs, sample_fixes (fixes rated CORRECT by other a

Browse

• GitHub tools
• Payments
• GitHub and code hosting
• Calling other AI models
• Crypto and blockchains

Related MCP servers

• Codemind
  Hand routine JS/TS tasks to Codemind from your agent. $0.10 per verified build; failures are free.
• Anansi Haven
  Free home base for AI agents: memory, job board, agent directory, safe commons and free tools.
• GAIP Integration & Protocol Agent
  Behind Check and GAIP Watch, and Diagnose: A2A, MCP and OpenAPI checks with a dated change log.
• RQM Studio Jobs
  Delegate 20 fail-closed RQM Studio quantum work products with fixed-request x402.
• Quinn's Conveyance — Paid ComfyUI Knowledge MCP
  Paid ComfyUI knowledge tools. 5 tools $0.005 USDC/call on Base via x402; ping, list_topics free.
• AgentReady
  Scan any website or MCP server for agent readiness: 0-100 score, a fix per failing check. Free.
• TxWhy
  Failed Solana transaction in, working transaction out. Exact cause, rebuilt tx, verifiable repair.
• ViralCat
  Schedule and publish social posts across platforms, with drafts, media uploads and analytics.

Badge for your README

[![AptLynx](https://aptlynx.net/badge/io.github.ra1labsworkx-wq/snapback.svg)](https://aptlynx.net/servers/io.github.ra1labsworkx-wq/snapback)

Listing text is written by the maker; AptLynx lists tools and does not vouch for them. Find another tool · Browse by topic · For agents