uspto_fpd_mcp (john-walkoe/uspto_fpd_mcp) is an MCP server listed on the M8ven Trust Index. M8ven has not graded it: there is no public source to read and no endpoint we can reach, so there is nothing for us to inspect. No publisher has claimed this listing.

Back to MCP Trust Indexm8ven
C
Emerging
74/100
13 days ago

uspto_fpd_mcp

→ john-walkoe/uspto_fpd_mcp· listed on modelscope

Emerging. No concerning findings. Grades remain capped until the project builds reputation through adoption. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.

How we verified

Code Verified⚡ Live Monitored: not connected

Verified is a snapshot. Live keeps it current, and builds your track record.

⚡ Connect GitHub → continuous verification on every pushwhy connect →

Who stands behind it

john-walkoe

Source: modelscope

Is this your MCP?

Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find. Or connect your repo for our deepest verification, Live Monitored: read-only, revoke anytime. What we access →

⚡ Connect GitHub for Live Monitored

Install from

modelscope

M8ven verifies MCPs across every public registry — install directly from whichever one you prefer.

// key findings
✅
10 tools verified — handlers match their declared behaviour
8 read-only tools verified — handlers contain no write/delete/exec
✅
No credential exfiltration, no sensitive file access, no obfuscation
Static analysis found nothing flowing your secrets to unexpected places.
✅
Open source with a license and README
Anyone can audit the code, the license is declared, and the publisher documents what it does.
🔐
You'll be asked for 9 credentials: PROXY_TOKEN, INTERNAL_AUTH_SECRET, USPTO_API_KEY, FPD_AUTH_JWT_SECRET, FPD_AUTH_GOOGLE_CLIENT_SECRET, FPD_AUTH_MS_CLIENT_SECRET, FPD_AUTH_INTERNAL_TOKEN, FPD_AUTH_INTERNAL_ADMIN_TOKEN, MISTRAL_API_KEY
These are read from process.env at runtime. Make sure you trust where they’ll be sent.
// environment variables
To run this server yourself, you supply these values. They go in your own MCP client configuration and stay on your machine. The secret label means the value is sensitive, not that the server mishandles it.
🔐 secretPROXY_TOKENauto Fixed proxy auth token for cross-process registration
configFPD_PROXY_PORT"": "8081"
configPROXY_PORT
configCORS_EXTRA_ORIGINunset Extra CORS origins for HTTP mode (e.g. https://claude.ai)
configPROXY_ALLOWED_IPSunset Extra client IPs/CIDRs allowed at the proxy (Docker subnets)
configFASTMCP_TRANSPORTstdio stdio (Claude Desktop) or http (Docker/claude.ai)
configFPD_AUTH_MODEnone none (default, no OAuth) or oauth (Google + Entra dual IdP, HTTP only)
configFPD_PROXY_BASE_URLunset Externally reachable proxy base URL (Docker/reverse proxy) — used in emitted persistent links
configMCP_APP_EXTRA_DOMAINSunset Extra CSP domains for MCP App iframes (comma-separated)
configFPD_AUTH_DB_PATHdata/mcp_auth.db SQLite user database; may be shared across MCP servers on the same host
configFPD_ENABLE_USER_MANAGEMENTfalse Enable admin-tool registration; must be true in OAuth deployments
configCENTRALIZED_PROXY_PORT"": "none",
🔐 secretINTERNAL_AUTH_SECRETunset Required in HTTP mode (X-API-KEY auth); also signs centralized-proxy JWTs — must match PFW's
configFASTMCP_HOST127.0.0.1 HTTP bind address
configFASTMCP_PORT8000 HTTP port (cluster convention: fpd = 8005)
configENABLE_ALWAYS_ON_PROXYtrue Start the proxy at startup vs on-demand
configENABLE_PROXY_SERVERtrue Enable the local download proxy
configLOG_LEVELINFO Logging level. Logs record flow metadata only — never query text, response bodies, OCR text, or link hashes
configDOCLING_SERVE_URLunset Enables Docling OCR tier (e.g. https://docling.example.com)
configDOCLING_TIMEOUT300 Docling read timeout (seconds)
configDOCLING_MAX_PAGES25 Skip Docling above this page count (petition decisions are short)
🔐 secretUSPTO_API_KEY"": "your_actual_USPTO_api_key_here",
configUSPTO_TIMEOUT30.0 API request timeout (seconds)
configUSPTO_DOWNLOAD_TIMEOUT60.0 PDF download timeout (seconds)
configFPD_AUTH_BASE_URLunset Public HTTPS origin (required if FPD_AUTH_MODE=oauth)
🔐 secretFPD_AUTH_JWT_SECRETunset JWT signing secret (required if FPD_AUTH_MODE=oauth; generate with openssl rand -hex 32)
configFPD_AUTH_GOOGLE_CLIENT_ID/ _SECRET unset Google OAuth credentials (optional; omit if using Entra only)
🔐 secretFPD_AUTH_GOOGLE_CLIENT_SECRET
configFPD_AUTH_MS_CLIENT_ID/ _SECRET unset Entra (Microsoft) OAuth credentials (optional; omit if using Google only)
🔐 secretFPD_AUTH_MS_CLIENT_SECRET
configFPD_AUTH_MS_TENANTcommon Entra tenant: common (any tenant), organizations (work/school only), or tenant GUID
🔐 secretFPD_AUTH_INTERNAL_TOKENunset Static bearer token for headless clients (grants fpd:user scope only)
🔐 secretFPD_AUTH_INTERNAL_ADMIN_TOKENunset Separate static bearer for machine clients requiring admin scope (grants fpd:user + fpd:admin)
configFPD_AUTH_REGISTER_URLunset Optional "Request access" link shown on sign-in screen
configFPD_AUTH_ACCESS_TTL3600 Access token lifetime (seconds; default 1 hour)
configFPD_AUTH_REFRESH_TTL2592000 Refresh token lifetime (seconds; default 30 days, idle timeout)
configLOG_DIR~/.uspto_fpd_mcp/logs Log directory override (Docker volumes)
configFPD_LOG_MAX_BYTES/ FPD_LOG_BACKUP_COUNT 10485760 / 5 File log rotation
configFPD_LOG_BACKUP_COUNTFPD_LOG_MAX_BYTES / 10485760 / 5 File log rotation
configCENTRALIZED_PROXY_URL
configMISTRAL_OCR_DAILY_BUDGET_USDunset (unlimited) Cumulative daily spend ceiling for Mistral OCR calls; resets at UTC midnight
🔐 secretMISTRAL_API_KEY"": "your_mistral_api_key_here_OPTIONAL",
configMISTRAL_OCR_MODEL"": "mistral-ocr-latest_OPTIONAL_pin_a_dated_slug",
configENVIRONMENT
configUSPTO_SHARED_RATE_LIMIT_RPS4.0 Token bucket rate (tokens/sec, shared across all 4 USPTO MCPs)
configUSPTO_SHARED_MAX_CONCURRENT2 Concurrency slots (shared in-flight requests across all 4 MCPs)
configUSPTO_SHARED_RATE_LIMIT_DIRunset Enable cross-process rate limiter; bind-mounted directory (unset = disabled)
configUSPTO_DB_JOURNAL_MODE
// quality suggestions

Tool annotations

8/10 tools have annotations

Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.

All four hints declared on every tool

10/10 tools missing one or more hints — FPD_manage_users (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); FPD_get_document_download (missing: destructiveHint, idempotentHint, openWorldHint); FPD_get_document_content_with_mistral_ocr (missing: destructiveHint, idempotentHint, openWorldHint), +7 more. OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.

For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.

Tool inputs are validated

9/10 tool handlers declare input schemas (90%)

Declare an inputSchema with zod/joi/yup on every tool definition.

Tool test coverage

5/10 tools referenced in tests (50%)

Write tests that reference each tool by name so every tool has at least one test.

Claim the listing to review these findings one by one and send us a correction where you disagree, straight to the team. Claiming also means we tell you when the grade moves, and reach you first if we find anything urgent.

// full audit trail
The findings above are the summary. The full trail, every check we ran, each deduction, the network hosts observed and the dependency advisories, goes to verified publishers, along with an alert whenever a new one lands. Verified publishers can also review each finding and dispute it in one click. Publisher corrections have sharpened several of our checks this month, because the maintainer knows the codebase better than any scanner.
// improvement guidance — verified publishers only
We have 4 concrete improvements we can share with the publisher of this MCP. Each comes with specific guidance to raise the trust score.
// embed badge in your README
[![M8ven Score](https://m8ven.ai/badge/mcp/john-walkoe-uspto-fpd-mcp-1r4trg)](https://m8ven.ai/mcp/john-walkoe-uspto-fpd-mcp-1r4trg)
Shows your grade and updates automatically. Prefer no grade? Append ?variant=verified to the badge URL.
commit: 3190a0603da13a364becaaa9b4bf883033db9619
code hash: 104af0b8090a5b7a0c1b5ae80d82a97795f03659100e93b340a33c8eede4cc49
verified: 8/13/2026, 10:09:37 PM
view raw JSON →
Check MCPs from inside your assistant
Tool Check · MCP

Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.

https://m8ven.ai/api/mcp/tool-check
check_toolsearch_toolscompare_toolsrecommend_alternativescheck_publisherreport_concern
How to add it →Free · no account needed · works in any MCP client