MCP Server

Snapback

io.github.ra1labsworkx-wq/snapback
AI & Agents Developer Tools Public & reachable MCP 2026-07-28

What this MCP does

Diagnoses agent failures, detects loops and budget issues, recommends recovery or failover actions, and maintains a shared fix library.

agent_memory
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 your own agent. Free.
Read only Idempotent
Input schema
{'type': 'object', 'required': [], 'properties': {'limit': {'type': 'integer', 'description': 'top N patterns (default 5)'}}}
Output schema
{'type': 'object', 'description': 'A JSON object (returned as text in result.content[0].text). Diagnosis tools return {matched, family, fix, confidence, source, action_class, auto_safe, gate}; other tools return their own JSON result.', 'additionalProperties': True}
budget_guard
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. Advisory only (never blocks). Params: step, max_steps, tokens_used, token_budget, cost_used_usd, cost_budget_usd, context_used, context_window.
Read only Idempotent
Input schema
{'type': 'object', 'required': [], 'properties': {'step': {'type': 'integer'}, 'task': {'type': 'string'}, 'format': {'enum': ['full', 'summary', 'summary_only'], 'type': 'string', 'description': "'summary' adds a one-line relayable answer (for chat/Telegram agents); 'summary_only' returns just that line. Default full."}, 'max_steps': {'type': 'integer'}, 'tokens_used': {'type': 'number'}, 'context_used': {'type': 'number'}, 'token_budget': {'type': 'number'}, 'cost_used_usd': {'type': 'number'}, 'context_window': {'type': 'number'}, 'recent_actions': {'type': 'array'}, 'cost_budget_usd': {'type': 'number'}}}
Output schema
{'type': 'object', 'description': 'A JSON object (returned as text in result.content[0].text). Diagnosis tools return {matched, family, fix, confidence, source, action_class, auto_safe, gate}; other tools return their own JSON result.', 'additionalProperties': True}
cascade_root
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 {error, retried, action}. Free, no token, no LLM.
Read only Idempotent
Input schema
{'type': 'object', 'required': ['errors'], 'properties': {'errors': {'type': 'array', 'description': 'ordered list (oldest first) of error strings or {error, retried:bool, action} objects'}}}
Output schema
{'type': 'object', 'description': 'A JSON object (returned as text in result.content[0].text). Diagnosis tools return {matched, family, fix, confidence, source, action_class, auto_safe, gate}; other tools return their own JSON result.', 'additionalProperties': True}
convert_trace
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 straight to diagnose_trace. Free, no token.
Read only Idempotent
Input schema
{'type': 'object', 'required': ['source'], 'properties': {'hint': {'type': 'string', 'description': "optional: the framework/format, e.g. 'otel', 'openai'"}, 'source': {'description': 'your logs: a list, or an object wrapping a spans/steps/messages array'}}}
Output schema
{'type': 'object', 'description': 'A JSON object (returned as text in result.content[0].text). Diagnosis tools return {matched, family, fix, confidence, source, action_class, auto_safe, gate}; other tools return their own JSON result.', 'additionalProperties': True}
detect_loop
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.
Read only Idempotent
Input schema
{'type': 'object', 'required': ['steps'], 'properties': {'steps': {'type': 'array', 'description': 'your recent steps (last ~5-10), each with an action/tool and optionally inputs — same step shape as diagnose_trace'}, 'threshold': {'type': 'integer', 'description': 'how many identical consecutive calls = a loop (default 3)'}}}
Output schema
{'type': 'object', 'description': 'A JSON object (returned as text in result.content[0].text). Diagnosis tools return {matched, family, fix, confidence, source, action_class, auto_safe, gate}; other tools return their own JSON result.', 'additionalProperties': True}
diagnose_batch
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.
Read only Open world Idempotent
Input schema
{'type': 'object', 'required': ['traces'], 'properties': {'traces': {'type': 'array', 'description': 'array of trace objects (max 20)'}}}
Output schema
{'type': 'object', 'description': 'A JSON object (returned as text in result.content[0].text). Diagnosis tools return {matched, family, fix, confidence, source, action_class, auto_safe, gate}; other tools return their own JSON result.', 'additionalProperties': True}
diagnose_infra_error
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, failure_class, root_cause, fix, confidence, source, action_class, auto_safe, gate} instantly from the library (no LLM) when a known pattern matches. Free and no token. GATE CONTRACT for autonomous action: auto-apply the fix ONLY when confidence>=0.85 AND source=='library' AND auto_safe==true (action_class is retry|refetch|config); NEVER auto-apply a 'mutate' or 'destructive' fix (create/change state, money, auth) — escalate those to a human. gate.auto_apply_ok gives you the verdict. Use it the moment you hit a transaction_simulation_failed, BlockhashNotFound, a -32xxx RPC code, a 4001/-32002 wallet error, an attestation failure, or any infra error you can't instantly resolve.
Read only Open world Idempotent
Input schema
{'type': 'object', 'required': ['error'], 'properties': {'error': {'type': 'string', 'description': 'the exact error text/message you hit'}, 'action': {'type': 'string', 'description': 'optional: the tool/operation that failed'}, 'format': {'enum': ['full', 'summary', 'summary_only'], 'type': 'string', 'description': "'summary' adds a one-line relayable answer (for chat/Telegram agents); 'summary_only' returns just that line. Default full."}, 'context': {'type': 'string', 'description': "optional: what you were doing (e.g. 'paying via x402 on solana')"}}}
Output schema
{'type': 'object', 'description': 'A JSON object (returned as text in result.content[0].text). Diagnosis tools return {matched, family, fix, confidence, source, action_class, auto_safe, gate}; other tools return their own JSON result.', 'additionalProperties': True}
diagnose_trace
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 treat this as async (don't block your agent loop on it).
Read only Open world Idempotent
Input schema
{'type': 'object', 'required': ['trace'], 'properties': {'trace': {'type': 'object', 'description': 'OTel-shaped agent trace'}}}
Output schema
{'type': 'object', 'description': 'A JSON object (returned as text in result.content[0].text). Diagnosis tools return {matched, family, fix, confidence, source, action_class, auto_safe, gate}; other tools return their own JSON result.', 'additionalProperties': True}
get_request_status
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.
Read only Idempotent
Input schema
{'type': 'object', 'required': ['request_id'], 'properties': {'request_id': {'type': 'string'}}}
Output schema
{'type': 'object', 'description': 'A JSON object (returned as text in result.content[0].text). Diagnosis tools return {matched, family, fix, confidence, source, action_class, auto_safe, gate}; other tools return their own JSON result.', 'additionalProperties': True}
get_verdict
Fetch a previously produced verdict by its id or by trace_id (your org only).
Read only Idempotent
Input schema
{'type': 'object', 'required': [], 'properties': {'trace_id': {'type': 'string'}, 'verdict_id': {'type': 'string'}}}
Output schema
{'type': 'object', 'description': 'A JSON object (returned as text in result.content[0].text). Diagnosis tools return {matched, family, fix, confidence, source, action_class, auto_safe, gate}; other tools return their own JSON result.', 'additionalProperties': True}
my_impact
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.
Read only Idempotent
Input schema
{'type': 'object', 'required': [], 'properties': {}}
Output schema
{'type': 'object', 'description': 'A JSON object (returned as text in result.content[0].text). Diagnosis tools return {matched, family, fix, confidence, source, action_class, auto_safe, gate}; other tools return their own JSON result.', 'additionalProperties': True}
my_usage
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.
Read only Idempotent
Input schema
{'type': 'object', 'required': [], 'properties': {}}
Output schema
{'type': 'object', 'description': 'A JSON object (returned as text in result.content[0].text). Diagnosis tools return {matched, family, fix, confidence, source, action_class, auto_safe, gate}; other tools return their own JSON result.', 'additionalProperties': True}
preflight
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.
Read only Idempotent
Input schema
{'type': 'object', 'required': [], 'properties': {'tags': {'type': 'array', 'items': {'type': 'string'}, 'description': 'task facets, e.g. [tool_calling, retrieval] (optional)'}, 'limit': {'type': 'integer', 'description': 'max cards (default 10)'}, 'agent_stack': {'type': 'string', 'description': 'e.g. openclaw, langchain (optional)'}}}
Output schema
{'type': 'object', 'description': 'A JSON object (returned as text in result.content[0].text). Diagnosis tools return {matched, family, fix, confidence, source, action_class, auto_safe, gate}; other tools return their own JSON result.', 'additionalProperties': True}
recommend_failover
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 retried 5x when you should switch to Base. Free, no token, no LLM. Reads only what you tell it (no network calls).
Read only Open world Idempotent
Input schema
{'type': 'object', 'required': ['error'], 'properties': {'error': {'type': 'string', 'description': 'the error you hit'}, 'current_chain': {'type': 'string', 'description': "the chain you're on (e.g. 'solana')"}, 'available_chains': {'type': 'array', 'items': {'type': 'string'}, 'description': "fallback chains you can use (e.g. ['base','arbitrum'])"}, 'current_provider': {'type': 'string', 'description': "the RPC/provider you're using (e.g. 'helius')"}, 'available_providers': {'type': 'array', 'items': {'type': 'string'}, 'description': 'backup providers on the same chain'}}}
Output schema
{'type': 'object', 'description': 'A JSON object (returned as text in result.content[0].text). Diagnosis tools return {matched, family, fix, confidence, source, action_class, auto_safe, gate}; other tools return their own JSON result.', 'additionalProperties': True}
report_outcome
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 feeds the shared crowd view — every reported outcome makes what_others_did sharper for the next agent. Token-scoped (so we know it's your org), free.
Open world
Input schema
{'type': 'object', 'required': ['failure_class', 'succeeded'], 'properties': {'fix': {'type': 'string', 'description': 'the fix that was auto-applied'}, 'family': {'type': 'string'}, 'succeeded': {'type': 'boolean', 'description': 'did the single retry after the fix succeed?'}, 'confidence': {'type': 'number'}, 'action_class': {'type': 'string', 'description': 'retry | refetch | config'}, 'failure_class': {'type': 'string'}}}
Output schema
{'type': 'object', 'description': 'A JSON object (returned as text in result.content[0].text). Diagnosis tools return {matched, family, fix, confidence, source, action_class, auto_safe, gate}; other tools return their own JSON result.', 'additionalProperties': True}
request_pattern
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 roadmap/backlog. Free — no token needed.
Open world
Input schema
{'type': 'object', 'required': ['message'], 'properties': {'kind': {'type': 'string', 'description': "'pattern_request' | 'problem' | 'message' (default 'message')"}, 'context': {'type': 'object', 'description': "optional: the trace/error you couldn't get diagnosed (redacted server-side)"}, 'message': {'type': 'string', 'description': "what you'd like added, or the problem we couldn't solve — be specific"}, 'verdict_id': {'type': 'string', 'description': 'optional: the verdict this relates to'}}}
Output schema
{'type': 'object', 'description': 'A JSON object (returned as text in result.content[0].text). Diagnosis tools return {matched, family, fix, confidence, source, action_class, auto_safe, gate}; other tools return their own JSON result.', 'additionalProperties': True}
search_docs
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.
Read only Open world Idempotent
Input schema
{'type': 'object', 'required': ['query'], 'properties': {'limit': {'type': 'integer', 'description': 'max sections to return (default 3)'}, 'query': {'type': 'string', 'description': "what you want to know, e.g. 'how to format a trace'"}}}
Output schema
{'type': 'object', 'description': 'A JSON object (returned as text in result.content[0].text). Diagnosis tools return {matched, family, fix, confidence, source, action_class, auto_safe, gate}; other tools return their own JSON result.', 'additionalProperties': True}
session_end
Close a live session and get a short run summary (total steps, duration). Frees the session. Free, no token.
Input schema
{'type': 'object', 'required': ['session_id'], 'properties': {'session_id': {'type': 'string'}}}
Output schema
{'type': 'object', 'description': 'A JSON object (returned as text in result.content[0].text). Diagnosis tools return {matched, family, fix, confidence, source, action_class, auto_safe, gate}; other tools return their own JSON result.', 'additionalProperties': True}
session_start
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.
Input schema
{'type': 'object', 'required': [], 'properties': {'agent_id': {'type': 'string', 'description': 'optional label for your agent/run'}}}
Output schema
{'type': 'object', 'description': 'A JSON object (returned as text in result.content[0].text). Diagnosis tools return {matched, family, fix, confidence, source, action_class, auto_safe, gate}; other tools return their own JSON result.', 'additionalProperties': True}
session_step
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_window). Warnings are advisory - act on them to self-correct mid-run. Free.
Input schema
{'type': 'object', 'required': ['session_id', 'step'], 'properties': {'step': {'type': 'object', 'description': 'the step: action/tool + inputs'}, 'counters': {'type': 'object', 'description': 'running counters (tokens/cost/context/max_steps)'}, 'session_id': {'type': 'string'}, 'loop_threshold': {'type': 'integer', 'description': 'identical calls that count as a loop (default 3)'}}}
Output schema
{'type': 'object', 'description': 'A JSON object (returned as text in result.content[0].text). Diagnosis tools return {matched, family, fix, confidence, source, action_class, auto_safe, gate}; other tools return their own JSON result.', 'additionalProperties': True}
submit_feedback
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 anonymized so every agent benefits; your trace content is never shared) — a right verdict comes back faster next time, a wrong one gets down-weighted. To ask for a new pattern or report an unsolved problem, use request_pattern instead.
Open world
Input schema
{'type': 'object', 'required': ['verdict_id', 'correct'], 'properties': {'note': {'type': 'string', 'description': 'optional free-text: what worked, what was wrong, or any detail that would help us improve this verdict'}, 'correct': {'type': 'boolean', 'description': 'true if the diagnosis was right, false if not'}, 'verdict_id': {'type': 'string', 'description': "the verdict you're rating"}}}
Output schema
{'type': 'object', 'description': 'A JSON object (returned as text in result.content[0].text). Diagnosis tools return {matched, family, fix, confidence, source, action_class, auto_safe, gate}; other tools return their own JSON result.', 'additionalProperties': True}
suggest_budget_recovery
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 about it'. Free, no token, no LLM.
Read only Idempotent
Input schema
{'type': 'object', 'required': [], 'properties': {'tokens_used': {'type': 'number'}, 'context_used': {'type': 'number'}, 'token_budget': {'type': 'number'}, 'cost_used_usd': {'type': 'number'}, 'context_window': {'type': 'number'}, 'recent_actions': {'type': 'array', 'items': {'type': 'string'}}, 'cost_budget_usd': {'type': 'number'}}}
Output schema
{'type': 'object', 'description': 'A JSON object (returned as text in result.content[0].text). Diagnosis tools return {matched, family, fix, confidence, source, action_class, auto_safe, gate}; other tools return their own JSON result.', 'additionalProperties': True}
what_others_did
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 agents)}. Use it when you hit a failure and want the crowd's verdict on what actually fixes it, not just the single library answer. Free, no token. Privacy-safe: only aggregate counts + a community success rate + the working fixes — never any org, agent, or trace identity. Hidden below a small min-sample so a single report can't be reverse-engineered. This is the network effect: the more agents use Snapback, the sharper this answer gets.
Read only Open world Idempotent
Input schema
{'type': 'object', 'required': [], 'properties': {'error': {'type': 'string', 'description': "optional: an error string — we'll diagnose it to find the failure_class, then return the crowd outcomes for it"}, 'failure_class': {'type': 'string', 'description': "the failure_class to look up (e.g. 'unhandled_tool_error', 'loop_repeated_tool_call'); or pass 'error' and we map it"}}}
Output schema
{'type': 'object', 'description': 'A JSON object (returned as text in result.content[0].text). Diagnosis tools return {matched, family, fix, confidence, source, action_class, auto_safe, gate}; other tools return their own JSON result.', 'additionalProperties': True}
Changed
diagnose_infra_error
Oct. 4, 2026, 2:41 a.m.
Changed
search_docs
Oct. 4, 2026, 2:41 a.m.
Changed
convert_trace
Oct. 4, 2026, 2:41 a.m.
Changed
budget_guard
Oct. 4, 2026, 2:41 a.m.
Changed
agent_memory
Oct. 4, 2026, 2:41 a.m.
Changed
session_end
Oct. 4, 2026, 2:41 a.m.
Changed
session_step
Oct. 4, 2026, 2:41 a.m.
Changed
session_start
Oct. 4, 2026, 2:41 a.m.
Changed
detect_loop
Oct. 4, 2026, 2:41 a.m.
Changed
request_pattern
Oct. 4, 2026, 2:41 a.m.
Changed
suggest_budget_recovery
Oct. 4, 2026, 2:41 a.m.
Changed
cascade_root
Oct. 4, 2026, 2:41 a.m.
Changed
recommend_failover
Oct. 4, 2026, 2:41 a.m.
Changed
report_outcome
Oct. 4, 2026, 2:41 a.m.
Changed
what_others_did
Oct. 4, 2026, 2:41 a.m.
Changed
my_impact
Oct. 4, 2026, 2:41 a.m.
Changed
my_usage
Oct. 4, 2026, 2:41 a.m.
Changed
get_request_status
Oct. 4, 2026, 2:41 a.m.
Changed
submit_feedback
Oct. 4, 2026, 2:41 a.m.
Changed
preflight
Oct. 4, 2026, 2:41 a.m.
Changed
get_verdict
Oct. 4, 2026, 2:41 a.m.
Changed
diagnose_batch
Oct. 4, 2026, 2:41 a.m.
Changed
diagnose_trace
Oct. 4, 2026, 2:41 a.m.
Added
diagnose_infra_error
Sept. 22, 2026, 2:40 a.m.
Added
search_docs
Sept. 22, 2026, 2:40 a.m.
Added
convert_trace
Sept. 22, 2026, 2:40 a.m.
Added
budget_guard
Sept. 22, 2026, 2:40 a.m.
Added
agent_memory
Sept. 22, 2026, 2:40 a.m.
Added
session_end
Sept. 22, 2026, 2:40 a.m.
Added
session_step
Sept. 22, 2026, 2:40 a.m.