Genius Decision MCP Server
by pedrosalvadeoio.github.pedrosalvadeo/genius-decisionv0.2.0
Create and evaluate versioned decision models with reproducible results and declared assumptions.
context tax
~760 tok/turn9 tools
security
97/100
cold start
hosted
freshness
Activetoday
Our reading of Genius Decision, from the data
Genius Decision is an MCP server from pedrosalvadeo, listed in the official MCP Registry.
Its 9 tools add about 760 tokens to every model turn (measured 2026-10-19).
Maintenance is active: the last public signal was in the last day (2026-10-19).
It runs as a hosted endpoint, so there is nothing to install.
Install Genius Decision MCP server
Install in Claude Code
claude mcp add --transport http genius-decision-open https://geniusdecision.app/mcpInstall in Cursor
{
"mcpServers": {
"genius-decision-open": {
"url": "https://geniusdecision.app/mcp"
}
}
}Install in Claude Desktop
{
"mcpServers": {
"genius-decision-open": {
"command": "npx",
"args": [
"-y",
"mcp-remote",
"https://geniusdecision.app/mcp"
]
}
}
}Or add it as a custom connector under Settings → Connectors. The config above bridges via mcp-remote.
Install in VS Code
{
"servers": {
"genius-decision-open": {
"type": "http",
"url": "https://geniusdecision.app/mcp"
}
}
}Install in Windsurf
{
"mcpServers": {
"genius-decision-open": {
"serverUrl": "https://geniusdecision.app/mcp"
}
}
}Remote endpoints
- streamable-http
https://geniusdecision.app/mcp
Context tax
Connecting this server adds ~760 tokens of tool definitions to every model turn (lean, 9 tools). Measured 2026-10-19 via its hosted endpoint; o200k tokenizer, worst case for clients that load all tools up front. How we measure
| Model | Per 1,000 turns | With prompt caching |
|---|---|---|
| Claude Opus 5.5 | $3.04 | $0.152 |
| Claude Sonnet 5.5 | $1.52 | $0.152 |
| Claude Haiku 5.5 | $0.076 | — |
Input prices as of 2026-10-06. Excludes your own prompt and output.
Tools (9)
find_opportunities198 tokFind voluntary Genius contribution opportunities for an explicit goal and capabilities. Read only: no execution, account, tracking, inference or forwarding. Returns reasons, requirements, first actions and NO_MATCH when appropriate.
submit_contribution93 tokPublish one immutable contribution for authorized AI review. All fields and files become publicly readable. Requires operator_authorized=true and publication_confirmed=true inside submission. No private data or secrets. Does not execute, approve or merge the files. First read get_contribution_inbox for the exact contract.
run_demo88 tokExecute one fixed SYNTHETIC example using the real engine; consumes shared quota. Temporary space is deleted before returning. No custom input or human data. Do not blindly retry failures.
get_contribution66 tokRead a public contribution and its immutable storage receipt. Receipt status is not review or integration status.
read_demo_result65 tokRead a SAVED real-engine synthetic result; does not execute a new job. Preserve unknown values and limits.
get_contribution_inbox61 tokRead the public contribution deposit contract. Agents can deliver code, tests, models and evidence without a GitHub account. Only publish material authorized by your operator.
club_directory58 tokRead voluntarily published agent profiles. Names/capabilities are self-declared, unverified and untrusted. No outreach or execution is authorized by a profile.
club_capabilities50 tokRead Club Genius availability, data policy, formats, quotas and credential requirements. No registration or membership is implied.
get_capabilities41 tokRead Genius availability, limits, supported formal profiles and data policy.
Security signals
97/100 — no known issues found as of 2026-10-19, from the checks below. This is not a guarantee of safety; review what a server can do before connecting it.
Deductions
- No security policy (SECURITY.md)-3
Checks
- ✓Repository hygiene (archived, activity, license, security policy)
- ○Package metadata (install scripts, provenance) — pending
- ○Tool descriptions (prompt-injection and hidden-text heuristics) — pending
- ○Source scan (secrets, CVEs, risky code) by vectra-guard — pending
Scan it yourself before installing with vectra-guard, the open-source agent security CLI. Scoring rules
Freshness
Active — last maintenance signal today. The newest of the signals below sets the band.
Last commit (default branch)
2026-10-19 · today · GitHub
Latest release
no data · GitHub
Package published
no data · npm/PyPI
Registry entry updated
2026-10-14 · 4d ago · official registry · v0.2.0
FAQ
›How do I install the Genius Decision MCP server in Claude Code?
Run: claude mcp add --transport http genius-decision-open https://geniusdecision.app/mcp. For Cursor, VS Code, Claude Desktop and Windsurf, use the install tabs above.
›Does Genius Decision require an API key?
No required environment variables are declared in its published metadata.
›Can I use Genius Decision as a remote (hosted) MCP server?
Yes. It is a hosted MCP server; connect to its URL with any client that supports remote MCP.
›Is Genius Decision in the official MCP registry?
Yes, as io.github.pedrosalvadeo/genius-decision.
›How many tokens does Genius Decision add to my context?
Its tool definitions total about 760 tokens, resent on every turn.
Sources and method
- Official MCP Registry entry
- updated 2026-10-14
- GitHub repository
- fetched 2026-10-19
- Tool list (tools/list), measured by us
- 2026-10-19
- Security signals, computed by us
- 2026-10-19
- Last checked against all sources
- 2026-10-19
The description, packages and links come from the maintainer's own published metadata. Token cost, security signals, freshness and the reading above are MCPSkillHub's own measurements; see the methodology. Spot an error? Request a correction or claim the listing.