StackFast FractWin Expert Brain
REMOTE · STACKFAST.AI · SCANNED SEP 20
Expert knowledge base for sales, negotiation, strategy, operations, and risk.
Available components
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 Security94
- The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
- Authorisation is enforced on tool calls, advertised via RFC 9728 protected-resource metadata. Discovery is public, which costs nothing: no tool can be invoked without a token. View diagnostics → Pass
- HTTPS is enforced; there's no plaintext access path. View diagnostics → Pass
- The HSTS (Strict-Transport-Security) header is present. View diagnostics → Pass
- DNSSEC check failed: this domain isn't protected by DNSSEC. See how to fix → View diagnostics → Fail
- The authorisation server offers only Dynamic Client Registration (RFC 7591), which MCP 2026-07-28 deprecated in favour of Client ID Metadata Documents. View diagnostics → Partial
Transport & Reachability100
- Verified streamable-http transport via a live MCP handshake. View diagnostics → Pass
Schema Quality & AI Usability69
- 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
- AI-judged instruction clarity (good).Pass
- Context-footprint check failed: tool/resource definitions use about 14869 tokens (~195/item across 76 items; 74 tools + 2 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 Management99
- Stability check failed: schema churn in the 30 days we've observed: 0 tool removals, 1 breaking changes, 0 auth/transport breaks, 0 additions. See how to fix → Fail
Tool Coverage81
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 34% of tool parameters carry a description.Partial
- Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 74 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 76 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities73
- Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28. See how to fix → Fail
- Supports UI / widget rendering.Pass
How do I install the StackFast FractWin Expert Brain MCP server?
StackFast FractWin Expert Brain is a hosted endpoint at https://stackfast.ai/api/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 · stackfast.ai
claude mcp add --transport http trupe-rs-expert-brain 'https://stackfast.ai/api/mcp'
{
"mcpServers": {
"trupe-rs-expert-brain": {
"url": "https://stackfast.ai/api/mcp"
}
}
} {
"servers": {
"trupe-rs-expert-brain": {
"type": "http",
"url": "https://stackfast.ai/api/mcp"
}
}
} [mcp_servers.trupe-rs-expert-brain] url = "https://stackfast.ai/api/mcp"
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"trupe-rs-expert-brain": {
"type": "remote",
"url": "https://stackfast.ai/api/mcp",
"enabled": true
}
}
} openclaw mcp add trupe-rs-expert-brain --url 'https://stackfast.ai/api/mcp' --transport streamable-http
mcp_servers:
trupe-rs-expert-brain:
url: "https://stackfast.ai/api/mcp" {
"McpServers": {
"trupe-rs-expert-brain": {
"Transport": "http",
"Url": "https://stackfast.ai/api/mcp"
}
}
} assistant mcp add trupe-rs-expert-brain -t streamable-http -u 'https://stackfast.ai/api/mcp'
{
"mcpServers": {
"trupe-rs-expert-brain": {
"type": "http",
"url": "https://stackfast.ai/api/mcp"
}
}
} The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.
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.
- 15 Sept 26 0
- Stability: pass → fail ▼ security
- 7 Sept 26 0
- Stability: fail → pass ▲ security
- 31 Aug 26 0
- Tool “cogentcast_production_run” rewrote its description, which is the text the model reads security
- “cogentcast_production_run” added an optional parameter “dispatch_id” cosmetic
- “cogentcast_production_run” added an optional parameter “verification_task_id” cosmetic
- “cogentcast_production_run” added an optional parameter “verifier_job_id” cosmetic
- 30 Aug 26 0
- A breaking change shipped without a version bump: still 2026-07-09 ▼ security
- “cogentcast_package_create” added a required parameter “preview_digest”, so existing callers break ▼ functional
- “cogentcast_package_create” added an optional parameter “content_fingerprint” cosmetic
- “cogentcast_package_create” added an optional parameter “idempotency_key” cosmetic
- “cogentcast_package_create” added an optional parameter “input” cosmetic
- “cogentcast_package_create” added an optional parameter “preview_reference” cosmetic
- “cogentcast_package_create” added an optional parameter “source_hashes” cosmetic
- “cogentcast_package_preview” reworded the description of “input” cosmetic
- 26 Aug 26 +1
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
- 24 Aug 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 92 to 96.
- 23 Aug 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 89 to 92.
- 21 Aug 26 0
- Tool “cogentcast_approval_resolve” rewrote its description, which is the text the model reads security
- Tool “cogentcast_package_create” rewrote its description, which is the text the model reads security
- Tool “cogentcast_package_preview” rewrote its description, which is the text the model reads security
- Tool “cogentcast_production_run” rewrote its description, which is the text the model reads security
- Tool “cogentcast_production_status” rewrote its description, which is the text the model reads security
- New tool “dealership_check_lead_follow_up” functional
- New tool “dealership_sales_floor_brief” functional
- “cogentcast_production_run” added an optional parameter “chunk_id” cosmetic
- “cogentcast_production_run” added an optional parameter “manifest_sha256” cosmetic
- “cogentcast_production_status” reworded the description of “package_id” cosmetic
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 20 Sept 2026 · Probed https://stackfast.ai/api/mcp
TLS valid
Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .
| Subject | Issuer | Valid from | Valid until | Key | Signature | Serial |
|---|---|---|---|---|---|---|
| CN=stackfast.ai | CN=YR2,O=Let's Encrypt,C=US | 27 Jul 2026 | 25 Oct 2026 | RSA 2048 | SHA256-RSA | 5d531cb5a4e550ea8a5a03b0403f5f5e52e |
| SANs: stackfast.ai | ||||||
| CN=YR2,O=Let's Encrypt,C=US (CA) | CN=Root YR,O=ISRG,C=US | 3 Sept 2025 | 2 Sept 2028 | RSA 2048 | SHA256-RSA | 4ebd24947e24d394802d84a52fd5b319 |
| CN=Root YR,O=ISRG,C=US (CA) | CN=ISRG Root X1,O=Internet Security Research Group,C=US | 13 May 2026 | 2 Sept 2032 | RSA 4096 | SHA256-RSA | f24b6d17f9d9ad7cb1c9fea78782699f |
Background: What to check on a remote MCP endpoint →
DNSSEC insecure
Validation of stackfast.ai. — Not signed
| Zone | DS | Keys | Algorithms | Outcome |
|---|---|---|---|---|
| . | trust_anchor | 20326, 38696 | 8, 8 | Verified |
| ai. | present | 3799 | 8 | Verified |
| stackfast.ai. | absent | Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation |
Authentication Enforced and verified
The endpoint asked for a token and published valid RFC 9728 metadata describing how to get one.
| Result | Enforced and verified |
|---|---|
| Enforced | On tool calls |
| HTTP status | 200 |
WWW-Authenticate challenge Bearer resource_metadata="https://stackfast.ai/api/mcp/oauth-protected-resource", scope="read:stackfast offline_access"
Bearer resource_metadata="https://stackfast.ai/api/mcp/oauth-protected-resource", scope="read:stackfast offline_access"| Header | Value |
|---|---|
| strict-transport-security | max-age=31536000; includeSubDomains; preload |
| content-security-policy | default-src 'self'; script-src 'self' 'unsafe-inline' https://www.googletagmanager.com https://www.clarity.ms https://accounts.google.com; style-src 'self' 'unsafe-inline'; img-src 'self' data: blob: https:; font-src 'self' data: https://fonts.gstatic.com; connect-src 'self' https://stackfast.ai https://*.stackfast.ai https://*.vercel.app https://*.turso.io https://www.google-analytics.com https://www.google.com https://www.clarity.ms https://accounts.google.com; frame-src https://accounts.google.com; frame-ancestors 'none'; |
| x-content-type-options | nosniff |
| x-frame-options | DENY |
| referrer-policy | strict-origin-when-cross-origin |
| permissions-policy | camera=(), microphone=(), geolocation=() |
Protected resource metadata
| Document | https://stackfast.ai/api/mcp/oauth-protected-resource |
|---|---|
| Retrieved | Yes |
| Resource | https://stackfast.ai/api/mcp |
| Authorisation server | https://stackfast.ai |
Background: How OAuth 2.1 works in the 2026 MCP spec →
Transports 2 probes
| Transport | URL | Outcome | Status | Location |
|---|---|---|---|---|
| streamable-http | https://stackfast.ai/api/mcp | Verified | 200 | |
| http (plaintext) | http://stackfast.ai/api/mcp | HTTPS enforced | 308 | https://stackfast.ai/api/mcp |
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 →
talent_scout_upsert_campaign_profile Talent Scout Upsert Campaign Profile ~434
Create, update, activate, pause, or archive a saved Talent Scout direct-company discovery campaign. Campaigns define company lanes, role lanes, size, geography, comp floor, travel tolerance, negative filters, resume variant, voice anchor, and human-review requirements. Draft/review only; never sends or applies.
| Name | Type | Req | Description |
|---|---|---|---|
| acceptable_structures | array | – | – |
| auth_token_key | string | – | Optional wallet/env key name for the tenant Turso auth token. Never pass a raw token. |
| campaign_id | string | – | – |
| company_size_max | integer | – | – |
| company_size_min | integer | – | – |
| compensation_min | string | – | – |
| contact_strategy | object | – | – |
| database_url_key | string | – | Optional wallet/env key name for the tenant Turso database URL. Never pass a raw URL or secret. |
| eligible_countries | array | – | Backward-compatible campaign-level work-authorization hint. The stored owner policy still owns the hard country gate. |
| expanded_regions | array | – | – |
| expected_version | string | – | Optional optimistic concurrency token from campaign.updated_at. A mismatch fails without writing. |
| geography_anchor | string | – | – |
| minimum_total_comp | integer | – | – |
| name | string | – | – |
| negative_filters | array | – | – |
| priority | string | – | – |
| radius_minutes | integer | – | – |
| resume_variant_strategy | object | – | – |
| seed_robert_campaign | boolean | – | – |
| sqlite_path | string | – | Optional local SQLite path for BYOC receipts; hosted cloud calls fail closed instead of reading local files. |
| status | string | – | – |
| target_company_lanes | array | – | – |
| target_role_lanes | array | – | – |
| tenant_database_type | string | – | Optional physical database routing mode. Omit for the default internal StackFast DB; use sovereign_cloud only with wallet-resolved tenant DB credentials. |
| tenant_id | string | – | – |
| update_mode | string | – | Patch preserves omitted fields. Replace is explicit and may reapply defaults. |
| voice_anchor | string | – | – |
| Name | Type | Req | Description |
|---|---|---|---|
| drafts_never_sends | boolean | – | – |
| no_autonomous_outbound | boolean | – | – |
| public_tool | string | yes | – |
| result | object | – | – |
No examples provided.
voice_intelligence_run Voice Intelligence Run ~429
Run the voice intelligence orchestrator over any input: an uploaded or recorded audio/video file (base64 in file), a public audio or video URL (audio_or_video_url), a PDF (pdf), an image (image), or raw text/notes (text and/or notes). Provide exactly ONE input carrier — audio_or_video_url, file, pdf, image, or text/notes. The input is normalized to a transcript via the existing transcription rails, then three composed outputs are returned: a condensed summary (with action items, decisions, and a next step), a full-verbatim polished actual script (filler removed, wording preserved, never paraphrased; call sources return a masked summary instead), and an authority report (content flywheel plan, plus an owner-facing business report when business context is provided). All outward outputs are mask-gated.
| Name | Type | Req | Description |
|---|---|---|---|
| audio_or_video_url | string | – | Public audio or video URL to transcribe (YouTube caption rail or upload transcription). One of the five input carriers. |
| business | object | – | Optional GrowthOS business context. Providing business_name enables the owner-facing business report inside the authority report. |
| file | object | – | Uploaded or recorded audio/video (or text-carrying) file payload, base64-encoded. One of the five input carriers. |
| identity | object | – | Optional local identity used by the owner-facing business report. |
| image | object | – | Image payload, base64-encoded. One of the five input carriers. |
| notes | string | – | Alias for text input; merged with text when both are present. Counts as the text carrier. |
| object | – | PDF document payload, base64-encoded. One of the five input carriers. | |
| source | string | – | Optional input provenance. 'call' sources return a masked-summary actual script instead of full verbatim. |
| speaker | string | – | Optional primary speaker name. |
| text | string | – | Raw text input (transcription skipped). One of the five input carriers. |
| title | string | – | Optional title for the source material. |
| Name | Type | Req | Description |
|---|---|---|---|
| actual_script | object | yes | – |
| authority_report | object | yes | – |
| input_kind | string | yes | – |
| llm | object|null | – | – |
| receipts | array | yes | – |
| schema_version | string | yes | – |
| summary | object | yes | – |
| transcript | string | yes | – |
| transcript_source | string | yes | – |
No examples provided.
What is the StackFast FractWin Expert Brain MCP server?
StackFast FractWin Expert Brain is an MCP server listed in the public MCP registry as io.github.Trupe-Rs/expert-brain. Expert knowledge base for sales, negotiation, strategy, operations, and risk. This page covers its hosted endpoint (https://stackfast.ai/api/mcp).
Is the StackFast FractWin Expert Brain MCP server safe to use?
StackFast FractWin Expert Brain scores 89 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 StackFast FractWin Expert Brain MCP server expose?
StackFast FractWin Expert Brain exposes 74 tools: session_file_read, credentials_inventory, dealership_check_lead_follow_up, dealership_sales_floor_brief, audit_status, and 69 more. Their descriptions and schemas cost roughly 14,791 tokens of context every time the server is loaded.
Does the StackFast FractWin Expert Brain MCP server require authentication?
Yes. StackFast FractWin Expert Brain asked us for credentials when we connected, so you will need to authorise it in your MCP client before it can do anything.
Is the StackFast FractWin Expert Brain MCP server still maintained?
StackFast FractWin Expert Brain is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.