Skip to main content
Glama

Server Details

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

Ownership verified
Status
Healthy
Uptime
100.0% over the last 24 hours
Last Tested
Transport
Streamable HTTP · MCP 2025-03-26
URL
Repository
ra1labsworkx-wq/snapback-selfheal
GitHub Stars
0
ChatGPT
–
Claude
–

TDQS

A3.8/5.0

Scored across 23 tools

Disambiguation4/5

Most tools target a distinct stage (preflight, diagnose, batch, infra, sessions, guards, feedback, crowd) and descriptions work hard to differentiate them. However, session_step overlaps with both detect_loop and budget_guard (it returns loop/budget warnings itself), and report_outcome vs submit_feedback both feed outcome data, creating some boundary blur.

Naming Consistency4/5

Names are uniformly snake_case and cluster into clear families (diagnose_*, session_*, get_*, my_*). But the convention is not a single verb_noun pattern: several are noun_noun (agent_memory, budget_guard, my_impact) and session_* is noun_verb, so the shape varies even though it stays readable.

Tool Count3/5

23 tools is heavy and leans toward the borderline/over-scoped band. The domain is genuinely broad (diagnosis, live guarding, feedback, crowd intel), but the overlap between session_step, detect_loop, and budget_guard suggests a few tools could be merged.

Completeness4/5

The surface covers the full agent-failure lifecycle: preflight patterns, mid-run guards and sessions, single/batch/infra diagnosis, recovery advice, failover, feedback, crowd intel, and docs. Only minor gaps (e.g. no pattern update/delete, no explicit verdict history listing) keep it from a 5.

Publisher details

Operator
https://snapback.sh/legal/terms
Operator website
https://snapback.sh/
Vendor relationship
Not applicable
Privacy policy
Not provided
Trust center
Not applicable
Restrictions
No setup restrictions

Available Tools

23 tools
agent_memoryA
Read-onlyIdempotent
Inspect

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.

Inputs: limit. Returns: A JSON object (returned as text in result.content[0].text). Diagnosis tools ret…

budget_guardA
Read-onlyIdempotent
Inspect

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.

Inputs: step, task, format, max_steps, +7 more. Returns: A JSON object (returned as text in result.content[0].text). Diagnosis tools ret…

cascade_rootA
Read-onlyIdempotent
Inspect

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.

Inputs: errors (required). Returns: A JSON object (returned as text in result.content[0].text). Diagnosis tools ret…

convert_traceA
Read-onlyIdempotent
Inspect

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.

Inputs: source (required), hint. Returns: A JSON object (returned as text in result.content[0].text). Diagnosis tools ret…

detect_loopA
Read-onlyIdempotent
Inspect

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.

Inputs: steps (required), threshold. Returns: A JSON object (returned as text in result.content[0].text). Diagnosis tools ret…

diagnose_batchA
Read-onlyIdempotent
Inspect

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.

Inputs: traces (required). Returns: A JSON object (returned as text in result.content[0].text). Diagnosis tools ret…

diagnose_infra_errorA
Read-onlyIdempotent
Inspect

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.

Inputs: error (required), action, format, context. Returns: A JSON object (returned as text in result.content[0].text). Diagnosis tools ret…

diagnose_traceA
Read-onlyIdempotent
Inspect

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).

Inputs: trace (required). Returns: A JSON object (returned as text in result.content[0].text). Diagnosis tools ret…

get_request_statusA
Read-onlyIdempotent
Inspect

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.

Inputs: request_id (required). Returns: A JSON object (returned as text in result.content[0].text). Diagnosis tools ret…

get_verdictB
Read-onlyIdempotent
Inspect

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

Inputs: trace_id, verdict_id. Returns: A JSON object (returned as text in result.content[0].text). Diagnosis tools ret…

my_impactA
Read-onlyIdempotent
Inspect

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.

Inputs: no named parameters. Returns: A JSON object (returned as text in result.content[0].text). Diagnosis tools ret…

my_usageA
Read-onlyIdempotent
Inspect

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.

Inputs: no named parameters. Returns: A JSON object (returned as text in result.content[0].text). Diagnosis tools ret…

preflightA
Read-onlyIdempotent
Inspect

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.

Inputs: tags, limit, agent_stack. Returns: A JSON object (returned as text in result.content[0].text). Diagnosis tools ret…

recommend_failoverA
Read-onlyIdempotent
Inspect

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).

Inputs: error (required), current_chain, available_chains, current_provider, +1 more. Returns: A JSON object (returned as text in result.content[0].text). Diagnosis tools ret…

report_outcomeAInspect

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.

Inputs: succeeded (required), failure_class (required), fix, family, +3 more. Returns: A JSON object (returned as text in result.content[0].text). Diagnosis tools ret…

request_patternAInspect

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.

Inputs: message (required), kind, context, verdict_id. Returns: A JSON object (returned as text in result.content[0].text). Diagnosis tools ret…

search_docsA
Read-onlyIdempotent
Inspect

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.

Inputs: query (required), limit. Returns: A JSON object (returned as text in result.content[0].text). Diagnosis tools ret…

session_endAInspect

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

Inputs: session_id (required). Returns: A JSON object (returned as text in result.content[0].text). Diagnosis tools ret…

session_startAInspect

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.

Inputs: agent_id. Returns: A JSON object (returned as text in result.content[0].text). Diagnosis tools ret…

session_stepAInspect

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.

Inputs: step (required), session_id (required), counters, loop_threshold. Returns: A JSON object (returned as text in result.content[0].text). Diagnosis tools ret…

submit_feedbackAInspect

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.

Inputs: correct (required), verdict_id (required), note. Returns: A JSON object (returned as text in result.content[0].text). Diagnosis tools ret…

suggest_budget_recoveryA
Read-onlyIdempotent
Inspect

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.

Inputs: tokens_used, context_used, token_budget, cost_used_usd, +3 more. Returns: A JSON object (returned as text in result.content[0].text). Diagnosis tools ret…

what_others_didA
Read-onlyIdempotent
Inspect

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.

Inputs: error, failure_class. Returns: A JSON object (returned as text in result.content[0].text). Diagnosis tools ret…

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Related MCP Connectors

    Related MCP Servers

    • F
      license
      A
      quality
      D
      maintenance
      Enables LLM-driven agents to autonomously detect, diagnose, repair, verify, and prevent software and hardware failures on local and remote systems. Includes built-in safety checks and automatic rollbacks.
      15
      -
    Try in Browser

    Glama MCP Gateway

    Add one secure layer between your agents and this server.