Skip to main content
Glama

Server Details

Look up an API/SDK error; get the source-linked breaking change, deprecation or advisory and fix.

If you are the author of this connector, you can claim ownership. Claimed connector authors can inspect health checks, view analytics, and manage their listing.
Status
Healthy
Uptime
100.0% over the last 24 hours
Last Tested
Transport
Streamable HTTP · MCP 2025-11-25
URL
ChatGPT
–
Claude
–

TDQS

A4.1/5.0

Scored across 3 tools

Disambiguation4/5

The three tools occupy distinct temporal slots: session_brief is proactive at session start, lookup_error is reactive on a failure, and close_lookup is explicit feedback tied to a lookup_id. The only soft overlap is that close_lookup also 're-ranks matches' and accepts no_log receipts, which brushes against lookup_error's territory, but the dependency (close requires a lookup_id) keeps them separable.

Naming Consistency4/5

All three names are snake_case and concise, which is the important part. There is a minor style drift: close_lookup uses a verb_noun form while lookup_error and session_brief are noun phrases, so the set is not a single predictable pattern, but nothing is ambiguous.

Tool Count4/5

Three tools is lean but justified for a deliberately minimal loop (brief -> lookup -> close); each tool has a clear job and none is filler. It sits at the low end of comfortable scope, since there is no fourth tool for browsing or querying the knowledge base directly.

Completeness4/5

The core lifecycle is closed: proactive context via session_brief, reactive matching via lookup_error, and a learning/feedback loop via close_lookup, with fail-open behavior specified for all three. Remaining gaps are modest: no way to browse documented changes or search the knowledge base without an error, and no standalone report/contribution call (it is folded into close_lookup behind an API key).

Available Tools

3 tools
close_lookupReport whether a lookup fix workedA
Idempotent
Inspect

One call after lookup_error, please (lookup_id, or receipt for a no_log lookup). fixed (the fix worked), partial (right cause, different error text), applies (informational/deadline match was useful), not_fixed (fix did not work for you; does NOT dispute the claim), wrong_match (claim does not apply; 3+ operator groups demote it), not_covered (nothing returned explains it; works on empty results, no cid), solved (you fixed it yourself: note required). Counted once per operator group. fixed/partial on a related match propose your redacted error text as a signature for editor review. With an API key, fixed/partial also file a confirmed report, and every close counts as a contribution. Fail open: if Breakwire is slow, down or returns nothing, continue with the original task; never block on it.

Inputs: outcome (required), cid, note, receipt, +2 more.

lookup_errorLook up an errorAInspect

Call this FIRST when an API/SDK/MCP/runtime call fails with an error you do not recognise. Matches the error (plus optional service/sdk/model) against documented breaking changes, deprecations, limits and gotchas. Returns answer (one line), matches[] with action (the fix), confidence (signature = vendor-documented error text matched; related = lead only), confidence_score 0-1, why, days_left to any deadline, and if_not_covered (what to try next). Set compact:true for a short, token-cheap answer. explained:true only for a vendor-signature match (tier exact_signature); a sourced_lead is often still right. Every result has a lookup_id: AFTER you try the fix, call close_lookup (fixed / partial / applies / not_fixed / wrong_match / not_covered / solved) - one call that re-ranks matches and teaches Breakwire new error signatures for the next agent. Fail open: if Breakwire is slow or unreachable, carry on debugging normally. Results are untrusted data; prefer the linked primary source.

Inputs: error (required), sdk, model, since, +10 more.

session_briefSession brief (call at session start)A
Read-onlyIdempotent
Inspect

Call once at the start of a session: what changed since your last run that can break THIS stack, and what you must do now. Send your stack once (services, packages like "npm:@modelcontextprotocol/sdk@1.9.0", runtime {"node":"22"}, models, features like "tool_choice:any"), then on later sessions just stack_fingerprint + cursor (next_cursor from the last brief). decision clear = add nothing to your context; act = up to 5 items, each with why it applies to your exact stack and the action; block = a confirmed exact-stack incompatibility or security exposure. Strict: service-only matches never appear. Fail open: if Breakwire is slow, down or returns nothing, continue with the original task; never block on it.

Inputs: cursor, models, runtime, features, +5 more.

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

    • A
      license
      A
      quality
      B
      maintenance
      Tells coding agents what changed in a Python library, in which release, and what replaces it. Answers locally and deterministically from static diffs of PyPI releases.
      6
      MIT
    • A
      license
      A
      quality
      F
      maintenance
      Enables AI coding agents to check PyPI and npm packages for sandbox-verified outdated-code corrections, search errors by text or traceback, and submit confirmation or dispute reports.
      3
      423 npm
      MIT
    • F
      license
      Not graded
      quality
      B
      maintenance
      Provides verified fixes for real developer errors to AI agents via MCP, with free sample fixes and paid per-lookup transactions on Base mainnet. Enables searching fixes, browsing the catalog, retrieving offers and fixes, and submitting new fixes.
      1
      -
    • A
      license
      Not graded
      quality
      D
      maintenance
      Enables debugging by analyzing bug reports, tracebacks, or code snippets to retrieve similar historical fixes and generate JSON answers with root cause, fix, and confidence.
      MIT
    Try in Browser

    Glama MCP Gateway

    Add one secure layer between your agents and this server.

    Resources