Breakwire
REMOTE · BREAKWIRE.ORG
Look up an API/SDK error; get the source-linked breaking change, deprecation or advisory and fix.
Available components
Last scanned (1 hour ago)
Scores higher than 43% of remote servers
Reachable. Last reached 5 Nov 2026.
Category Developer Tools
How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →
Endpoint Security63
- The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
- No authorisation is required to call this server. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one. See how to fix → View diagnostics → Partial
- HTTPS enforcement could not be verified: the plaintext port answered with HTTP 405, which proves neither a plaintext path nor enforcement. View diagnostics → Unverified
- HSTS check failed: the Strict-Transport-Security header is absent. See how to fix → View diagnostics → Fail
- DNSSEC check failed: this domain isn't protected by DNSSEC. See how to fix → View diagnostics → Fail
Transport & Reachability100
- Verified streamable-http transport via a live MCP handshake. View diagnostics → Pass
Schema Quality & AI Usability51
- AI-judged instruction clarity (good).Pass
- Context-footprint check failed: tool/resource definitions use about 1156 tokens (~385/item across 3 items; 3 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management0
- Stability check failed: schema churn in the 8 days we've observed: 18 tool removals, 0 breaking changes, 0 auth/transport breaks, 1 additions. See how to fix → Fail
Tool Coverage85
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 55% of tool parameters carry a description.Partial
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 3 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 4 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a current MCP spec version (2026-07-28).Pass
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 5 Nov 26 0
- Server version: 0.12.4 → 0.12.19 functional
- 4 Nov 26 0
- Server version: 0.11.11 → 0.12.4 functional
- 30 Oct 26 0
- Server version: 0.11.0 → 0.11.11 functional
- 29 Oct 26 +7
- Stability: unverified → fail ▼ security
- Tool “stats” was removed ▼ security
- Tool “changes” was removed ▼ security
- Tool “check_stack” was removed ▼ security
- Tool “coverage_gaps” was removed ▼ security
- Tool “deadlines” was removed ▼ security
- Tool “digest” was removed ▼ security
- Tool “events” was removed ▼ security
- Tool “get_claim” was removed ▼ security
- Tool “list_services” was removed ▼ security
- Tool “list_unexplained” was removed ▼ security
- Tool “model_launches” was removed ▼ security
- Tool “report_outcome” was removed ▼ security
- Tool “search_claims” was removed ▼ security
- Tool “search_error” was removed ▼ security
- Tool “stack_alerts” was removed ▼ security
- Tool “submit_claim” was removed ▼ security
- Tool “subscribe_stack” was removed ▼ security
- Tool “watch” was removed ▼ security
- Authorization: unverified → partial ▲ security
- The server rewrote its instructions, which are the text every model session reads security
- Tool “close_lookup” rewrote its description, which is the text the model reads security
- Schema quality: 123 → 385 ▼ functional
- Schema quality: 123 → 380 ▼ functional
- Schema quality: 123 → 144 ▼ functional
- Tool coverage: 12% → 55% ▲ functional
- Tool coverage: 12% → 24% ▲ functional
- Stability: unverified → 0.03 ▲ functional
- Schema quality: fair → good functional
- Server version: 0.10.0 → 0.11.0 functional
- Server version: 0.9.0 → 0.10.0 functional
- Server version: 0.7.1 → 0.9.0 functional
- Server version: 0.6.0 → 0.7.1 functional
- New tool “session_brief” functional
- “close_lookup” added an optional parameter “evidence_type” cosmetic
- “close_lookup” added an optional parameter “receipt” cosmetic
- “check_stack” added an optional parameter “compact” cosmetic
- “check_stack” added an optional parameter “files” cosmetic
- “check_stack” added an optional parameter “include_related” cosmetic
- “check_stack” added an optional parameter “installed” cosmetic
- “check_stack” added an optional parameter “models” cosmetic
- “check_stack” added an optional parameter “strict” cosmetic
- “report_outcome” added an optional parameter “evidence_type” cosmetic
- “report_outcome” added an optional parameter “intervention” cosmetic
- “report_outcome” added an optional parameter “verification” cosmetic
- “search_error” added an optional parameter “context” cosmetic
- “search_error” added an optional parameter “cross_service” cosmetic
- “lookup_error” added an optional parameter “reflex” cosmetic
- “lookup_error” added an optional parameter “since” cosmetic
- “search_error” added an optional parameter “reflex” cosmetic
- “search_error” added an optional parameter “since” cosmetic
- “close_lookup” reworded the description of “lookup_id” cosmetic
- “search_error” reworded the description of “model” cosmetic
- “search_error” reworded the description of “service” cosmetic
- “close_lookup” made “lookup_id” optional cosmetic
- 28 Oct 26 54
First indexed and scored.
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 5 Nov 2026 · Probed https://breakwire.org/mcp
TLS valid
Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .
| Subject | Issuer | Valid from | Valid until | Key | Signature | Serial |
|---|---|---|---|---|---|---|
| CN=breakwire.org | CN=WE1,O=Google Trust Services,C=US | 28 Oct 2026 | 26 Jan 2027 | ECDSA 256 | ECDSA-SHA256 | c44e31ed0c5fe880ecd8dc26c882bad |
| SANs: breakwire.org, www.breakwire.org, *.www.breakwire.org | ||||||
| CN=WE1,O=Google Trust Services,C=US (CA) | CN=GTS Root R4,O=Google Trust Services LLC,C=US | 13 Dec 2023 | 20 Feb 2029 | ECDSA 256 | ECDSA-SHA384 | 7ff31977972c224a76155d13b6d685e3 |
| CN=GTS Root R4,O=Google Trust Services LLC,C=US (CA) | CN=GlobalSign Root CA,OU=Root CA,O=GlobalSign nv-sa,C=BE | 15 Nov 2023 | 28 Jan 2028 | ECDSA 384 | SHA256-RSA | 7fe530bf331343bedd821610493d8a1b |
Background: What to check on a remote MCP endpoint →
DNSSEC insecure
Validation of breakwire.org. — Not signed
| Zone | DS | Keys | Algorithms | Outcome |
|---|---|---|---|---|
| . | trust_anchor | 20326, 38696 | 8, 8 | Verified |
| org. | present | 725, 26974 | 8, 8 | Verified |
| breakwire.org. | absent | Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation |
Authentication No authorisation required
The endpoint answered without asking for a token. Anyone who knows the URL can reach it.
| Result | No authorisation required |
|---|---|
| HTTP status | 200 |
Background: How OAuth 2.1 works in the 2026 MCP spec →
Transports 2 probes
| Transport | URL | Outcome | Status | Location |
|---|---|---|---|---|
| streamable-http | https://breakwire.org/mcp | Verified | 200 | |
| http (plaintext) | http://breakwire.org/mcp | Inconclusive | 405 |
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
close_lookup Report whether a lookup fix worked ~269
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.
| Name | Type | Req | Description |
|---|---|---|---|
| cid | string | – | one of the returned claims; omit for not_covered/solved |
| evidence_type | string | – | what you observed; fixed defaults to remedy_tested (you applied the fix and the call worked) |
| lookup_id | string | – | lk_... from a logged lookup |
| note | string | – | – |
| outcome | string | yes | – |
| receipt | string | – | rc_... from a no_log lookup (persistence.receipt): closes it without the error text ever being stored |
No output schema declared.
No examples provided.
lookup_error Look up an error ~439
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.
| Name | Type | Req | Description |
|---|---|---|---|
| compact | boolean | – | Short answer: lookup_id, explained, answer, top 3 matches (cid, confidence, action, days_left, url), next steps |
| context | string | – | – |
| cross_service | boolean | – | Also return matches from other services |
| error | string | yes | – |
| log_miss | boolean | – | false = do not log a miss as a coverage gap |
| max_matches | integer | – | – |
| min_score | number | – | – |
| model | string | – | – |
| no_log | boolean | – | true = search only: nothing is stored (no lookup_id, no miss logging, no counters) |
| reflex | boolean | – | false = omit the AGENTS.md reflex line |
| sdk | string | – | – |
| sdk_version | string | – | – |
| service | string | – | Service slug (see list_services). Hard filter unless cross_service is true. |
| since | string | – | On a miss: list this service's changes since YYYY-MM-DD or Nd (default 30d) |
No output schema declared.
No examples provided.
session_brief Session brief (call at session start) ~282
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.
| Name | Type | Req | Description |
|---|---|---|---|
| budget_tokens | integer | – | response budget (default 600, about 2,400 bytes) |
| cursor | integer | – | next_cursor from your previous brief; omit on the first call |
| features | array | – | – |
| installed | object | – | {package: installed version} |
| models | array | – | – |
| packages | array | – | eco:name@version, e.g. npm:openai@4.52.0, pypi:mcp==1.9.0 |
| runtime | object | – | e.g. {"node":"22","python":"3.12"} |
| services | array | – | – |
| stack_fingerprint | string | – | – |
No output schema declared.
No examples provided.
How do I install the Breakwire MCP server?
Breakwire is a hosted endpoint at https://breakwire.org/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
remote · breakwire.org
claude mcp add --transport http org-breakwire-breakwire 'https://breakwire.org/mcp'
What is the Breakwire MCP server?
Breakwire is an MCP server listed in the public MCP registry as org.breakwire/breakwire. Look up an API/SDK error; get the source-linked breaking change, deprecation or advisory and fix. This page covers its hosted endpoint (https://breakwire.org/mcp).
Is the Breakwire MCP server safe to use?
Breakwire scores 61 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the Breakwire MCP server expose?
Breakwire exposes 3 tools: session_brief, lookup_error, close_lookup. Their descriptions and schemas cost roughly 990 tokens of context every time the server is loaded.
Does the Breakwire MCP server require authentication?
No. We connected to Breakwire without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.
Is the Breakwire MCP server still maintained?
Breakwire is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.