Search / io.github.Shxnque/quesen
Deterministic decision layer for autonomous agents: reproducible PROCEED/REVIEW/SKIP verdicts.
v1.10.2 · active · repository · descriptor JSON · versions
protogrid{
"mcpServers": {
"quesen": {
"type": "http",
"url": "https://web-production-3df26.up.railway.app/mcp",
"headers": {
"X-API-Key": "${X_API_KEY}"
}
}
}
}claude mcp add --transport http quesen https://web-production-3df26.up.railway.app/mcp --header "X-API-Key: ${X_API_KEY}"[mcp_servers.quesen]
url = "https://web-production-3df26.up.railway.app/mcp"
env_http_headers = { "X-API-Key" = "X_API_KEY" }
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"quesen": {
"type": "remote",
"url": "https://web-production-3df26.up.railway.app/mcp",
"enabled": true,
"headers": {
"X-API-Key": "{env:X_API_KEY}"
}
}
}
}{
"mcpServers": {
"quesen": {
"type": "http",
"url": "https://web-production-3df26.up.railway.app/mcp",
"headers": {
"X-API-Key": "${X_API_KEY}"
}
}
},
"deeplink": "cursor://anysphere.cursor-deeplink/mcp/install?name=quesen&config=eyJ0eXBlIjoiaHR0cCIsInVybCI6Imh0dHBzOi8vd2ViLXByb2R1Y3Rpb24tM2RmMjYudXAucmFpbHdheS5hcHAvbWNwIiwiaGVhZGVycyI6eyJYLUFQSS1LZXkiOiIke1hfQVBJX0tFWX0ifX0%3D"
}{
"servers": {
"quesen": {
"type": "http",
"url": "https://web-production-3df26.up.railway.app/mcp",
"headers": {
"X-API-Key": "${X_API_KEY}"
}
}
}
}{
"mcpServers": {
"quesen": {
"httpUrl": "https://web-production-3df26.up.railway.app/mcp",
"headers": {
"X-API-Key": "${X_API_KEY}"
}
}
}
}extensions:
"quesen":
enabled: true
name: "quesen"
type: streamable_http
uri: "https://web-production-3df26.up.railway.app/mcp"
headers:
"X-API-Key": "${X_API_KEY}"
timeout: 300
Placeholders to fill from your own secret store: ${X_API_KEY}. The registry never accepts secret values.
protocol.modernnewest supported version is 2025-03-26; 2026-07-28 not supported, older versions are deprecated until 2027-07-28protocol.statelessonly applies to 2026-07-28 serversprotocol.transportstreamable HTTPprotocol.list_ttlonly applies to 2026-07-28 serversauth.prm, auth.as_metadata, auth.cimdno remote uses OAuthauth.secret_in_urlno templated URLtools.descriptionsevery tool has a descriptiontools.description_lengthdescriptions are concisetools.schemasevery tool has an object input schematools.annotationsno tool declares readOnlyHint or destructiveHint, so clients cannot tell safe calls from risky onestools.directory_hintsno tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: quesen.health (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); quesen.validate (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); quesen.simulate (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); …tools.token_costabout 1,311 tokens to load every tooltools.api_dumptools are not a one-to-one API dumpstability.changesno tool changes in 30 daysstability.rug_pullno tool changed its meaning under the same namedeps.known_vulns, deps.mcp_sdk_version, deps.resolvableno npm or PyPI packageNo tool definition changes recorded. A server's first observation is its baseline; later probes record what changes.
Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed. How it is computed.
+repository +namespace-matches-repo -unreachable(4 failures) ~updated-34d-ago
Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed. How it is computed.
| remote | auth | reachable | uptime 30d | p50 | protocol | last ok |
|---|---|---|---|---|---|---|
https://web-production-3df26.up.railway.app/mcp streamable-http | none | no (4 failures) | 96% | 252 ms | 2025-03-26 | 2026-10-13 |
quesen.health | Liveness probe. Returns engine_version and transport. |
quesen.report | Post-decision outcome feedback. Accepts request_id + outcome (RUG/LOSS/OK/WIN/UNKNOWN) plus optional post-trade metadata. Aggregated deterministically for SKIP-rate vs realized-outcome correlation. |
quesen.simulate | Counterfactual scoring. Compare the baseline decision against a simulated decision under caller-supplied weights_override / thresholds_override. Free sales asset — not charged against key. |
quesen.validate | Deterministic pre-decision risk validation for autonomous agents. Returns PROCEED / REVIEW / SKIP plus risk_score, confidence, and named conflict triggers. Same input -> same output; every response embeds engine_version + weights + thresholds for full replay. |
quesen.version | Full engine configuration — weights, thresholds, versions. |
Schemas: list_tools.
{
"name": "io.github.Shxnque/quesen",
"_meta": {
"io.modelcontextprotocol.registry/publisher-provided": {
"tool": "mcp-publisher",
"notes": "Deterministic zero-LLM risk-decision engine. Same inputs -> same output. Includes Agent Settlement Protocol (ASP/1.0) with HTTP 402 + USDC-on-Base for autonomous-agent settlement.",
"version": "1.8.0"
}
},
"icons": [
{
"src": "https://raw.githubusercontent.com/Shxnque/quesen/main/.github/quesen-icon.png",
"sizes": [
"any"
],
"mimeType": "image/png"
}
],
"title": "Quesen Deterministic Agent Decision Layer",
"$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
"remotes": [
{
"url": "https://web-production-3df26.up.railway.app/mcp",
"type": "streamable-http",
"headers": [
{
"name": "X-API-Key",
"format": "string",
"isSecret": true,
"description": "Quesen API key issued via https://senueren.co.za/quesen. Required for quesen.validate / quesen.simulate / quesen.report; not required for quesen.health / quesen.version."
}
]
}
],
"version": "1.10.2",
"repository": {
"id": "1302084518",
"url": "https://github.com/Shxnque/quesen",
"source": "github"
},
"description": "Deterministic decision layer for autonomous agents: reproducible PROCEED/REVIEW/SKIP verdicts."
}