このMCPでできること
Diagnoses agent failures, detects loops and budget issues, recommends recovery or failover actions, and maintains a shared fix library.
機能
ツール
23
ツール
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.
入力スキーマ
{'type': 'object', 'required': [], 'properties': {'limit': {'type': 'integer', 'description': 'top N patterns (default 5)'}}}
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.
入力スキーマ
{'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'}}}
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.
入力スキーマ
{'type': 'object', 'required': ['errors'], 'properties': {'errors': {'type': 'array', 'description': 'ordered list (oldest first) of error strings or {error, retried:bool, action} objects'}}}
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.
入力スキーマ
{'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'}}}
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.
入力スキーマ
{'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)'}}}
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.
入力スキーマ
{'type': 'object', 'required': ['traces'], 'properties': {'traces': {'type': 'array', 'description': 'array of trace objects (max 20)'}}}
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.
入力スキーマ
{'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')"}}}
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).
入力スキーマ
{'type': 'object', 'required': ['trace'], 'properties': {'trace': {'type': 'object', 'description': 'OTel-shaped agent trace'}}}
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.
入力スキーマ
{'type': 'object', 'required': ['request_id'], 'properties': {'request_id': {'type': 'string'}}}
get_verdict
Fetch a previously produced verdict by its id or by trace_id (your org only).
入力スキーマ
{'type': 'object', 'required': [], 'properties': {'trace_id': {'type': 'string'}, 'verdict_id': {'type': 'string'}}}
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.
入力スキーマ
{'type': 'object', 'required': [], 'properties': {}}
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.
入力スキーマ
{'type': 'object', 'required': [], 'properties': {}}
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.
入力スキーマ
{'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)'}}}
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).
入力スキーマ
{'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'}}}
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.
入力スキーマ
{'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'}}}
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.
入力スキーマ
{'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'}}}
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.
入力スキーマ
{'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'"}}}
session_end
Close a live session and get a short run summary (total steps, duration). Frees the session. Free, no token.
入力スキーマ
{'type': 'object', 'required': ['session_id'], 'properties': {'session_id': {'type': 'string'}}}
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.
入力スキーマ
{'type': 'object', 'required': [], 'properties': {'agent_id': {'type': 'string', 'description': 'optional label for your agent/run'}}}
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.
入力スキーマ
{'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)'}}}
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.
入力スキーマ
{'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"}}}
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.
入力スキーマ
{'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'}}}
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.
入力スキーマ
{'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"}}}
履歴
最近のツール変更
追加
diagnose_infra_error
2026年9月22日2:40
追加
search_docs
2026年9月22日2:40
追加
convert_trace
2026年9月22日2:40
追加
budget_guard
2026年9月22日2:40
追加
agent_memory
2026年9月22日2:40
追加
session_end
2026年9月22日2:40
追加
session_step
2026年9月22日2:40
追加
session_start
2026年9月22日2:40
追加
detect_loop
2026年9月22日2:40
追加
request_pattern
2026年9月22日2:40
追加
suggest_budget_recovery
2026年9月22日2:40
追加
cascade_root
2026年9月22日2:40
追加
recommend_failover
2026年9月22日2:40
追加
report_outcome
2026年9月22日2:40
追加
what_others_did
2026年9月22日2:40
追加
my_impact
2026年9月22日2:40
追加
my_usage
2026年9月22日2:40
追加
get_request_status
2026年9月22日2:40
追加
submit_feedback
2026年9月22日2:40
追加
preflight
2026年9月22日2:40
追加
get_verdict
2026年9月22日2:40
追加
diagnose_batch
2026年9月22日2:40
追加
diagnose_trace
2026年9月22日2:40
関連MCP
類似のMCPサーバー
Andreax
io.github.moralito311-andr/andreax
Offers pay-per-call AI services for inference, agent and workflow design, OCR and transcription, code generation and review, clas…
IA-QA — 130+ QA & Dev Tools for AI Agents
io.github.JcJamet/ia-qa-toolbox
Provides deterministic QA, evaluation, testing, code analysis, prompt and RAG checks, model comparison, and web security diagnost…
CompletionKit
com.completionkit/evals
Runs prompt evaluation workflows over datasets using deterministic checks and LLM judges, with metrics, scoring runs, agreements,…
Replicate
io.github.pipeworx-io/replicate
Provides access to Replicate models, versions, collections, hardware, predictions, and deployments for running and managing hoste…
Huggingface
io.github.pipeworx-io/huggingface
Provides access to Hugging Face model, dataset, and Space metadata, alongside broader structured research and data-routing tools.
Ai Model Experiments
io.github.pipeworx-io/ai-model-experiments
Runs prompts across multiple AI models and compares their outputs, costs, latency, token usage, and errors.
rubrkit
com.rubrkit/rubrkit
Manages AI evaluation artifacts, rubric audits, eval runs, golden cases, proof reports, and drift monitoring for LLM outputs.
Hipocampo MCP
io.github.carrasquelalex1/hipocampo
Provides bilingual semantic memory, embeddings, graph links, code indexing and search, context preload, deduplication, compressio…