Connect

8 clients · secrets stay placeholders

JSON (mcpServers)Claude CodeCodexOpenCodeCursorVS CodeGemini CLIGoose

{
  "mcpServers": {
    "scoring": {
      "type": "http",
      "url": "https://mcp.sentinelsignal.io/mcp",
      "headers": {
        "x-sentinel-api-key": "${X_SENTINEL_API_KEY}"
      }
    }
  }
}

claude mcp add --transport http scoring https://mcp.sentinelsignal.io/mcp --header "x-sentinel-api-key: ${X_SENTINEL_API_KEY}"

[mcp_servers.scoring]
url = "https://mcp.sentinelsignal.io/mcp"
env_http_headers = { "x-sentinel-api-key" = "X_SENTINEL_API_KEY" }

{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "scoring": {
      "type": "remote",
      "url": "https://mcp.sentinelsignal.io/mcp",
      "enabled": true,
      "headers": {
        "x-sentinel-api-key": "{env:X_SENTINEL_API_KEY}"
      }
    }
  }
}

{
  "mcpServers": {
    "scoring": {
      "type": "http",
      "url": "https://mcp.sentinelsignal.io/mcp",
      "headers": {
        "x-sentinel-api-key": "${X_SENTINEL_API_KEY}"
      }
    }
  },
  "deeplink": "cursor://anysphere.cursor-deeplink/mcp/install?name=scoring&config=eyJ0eXBlIjoiaHR0cCIsInVybCI6Imh0dHBzOi8vbWNwLnNlbnRpbmVsc2lnbmFsLmlvL21jcCIsImhlYWRlcnMiOnsieC1zZW50aW5lbC1hcGkta2V5IjoiJHtYX1NFTlRJTkVMX0FQSV9LRVl9In19"
}

{
  "servers": {
    "scoring": {
      "type": "http",
      "url": "https://mcp.sentinelsignal.io/mcp",
      "headers": {
        "x-sentinel-api-key": "${X_SENTINEL_API_KEY}"
      }
    }
  }
}

{
  "mcpServers": {
    "scoring": {
      "httpUrl": "https://mcp.sentinelsignal.io/mcp",
      "headers": {
        "x-sentinel-api-key": "${X_SENTINEL_API_KEY}"
      }
    }
  }
}

extensions:
  "scoring":
    enabled: true
    name: "scoring"
    type: streamable_http
    uri: "https://mcp.sentinelsignal.io/mcp"
    headers:
      "x-sentinel-api-key": "${X_SENTINEL_API_KEY}"
    timeout: 300

Placeholders to fill from your own secret store: ${X_SENTINEL_API_KEY}. The registry never accepts secret values.

Quality 88 / 100good

protocol75 · weight 25

warn
protocol.modernnewest supported version is 2025-11-25; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
n/a
protocol.statelessonly applies to 2026-07-28 servers
pass
protocol.transportstreamable HTTP
n/a
protocol.list_ttlonly applies to 2026-07-28 servers

authorizationn/a · weight 15

n/a
auth.prm, auth.as_metadata, auth.cimdno remote uses OAuth
n/a
auth.secret_in_urlno templated URL

tool hygiene93 · weight 30

pass
tools.descriptionsevery tool has a description
pass
tools.description_lengthdescriptions are concise
pass
tools.schemasevery tool has an object input schema
pass
tools.annotations8 of 8 tools declare readOnlyHint or destructiveHint
warn
tools.directory_hints1 of 8 tools declare all four hints; missing: score_workflow (destructiveHint); score_batch (destructiveHint); get_limits (destructiveHint); …
pass
tools.token_costabout 724 tokens to load every tool
pass
tools.api_dumptools are not a one-to-one API dump

stability100 · weight 15

pass
stability.changesno tool changes in 30 days
pass
stability.rug_pullno tool changed its meaning under the same name

dependenciesn/a · weight 15

n/a
deps.known_vulns, deps.mcp_sdk_version, deps.resolvableno npm or PyPI package

8 tools, about 724 tokens to load them all · tool set 78e2553a7af0 · checked 2026-10-19 23:18 UTC

Tool changes

No 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.

Trust 43 / 100

no-repositoryunreachable

provenance45

liveness0

freshness65

hygiene80

+dns-namespace -unreachable(4 failures) ~updated-149d-ago -no-repository

Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed. How it is computed.

Endpoints

remote	auth	reachable	uptime 30d	p50	protocol	last ok
`https://mcp.sentinelsignal.io/mcp` streamable-http	none	no (4 failures)	96%	228 ms	2025-11-25	2026-10-13

Tools (8)

`get_limits`read-only	Retrieve plan limits, trial quota, and upgrade state via GET /v1/limits
`get_usage`read-only	Retrieve monthly scoring call usage via GET /v1/usage
`get_workflow_schema`read-only	Fetch required fields, optional fields, enums, and an example payload for a workflow via GET /v1/workflows/{workflow}/schema
`list_workflows`read-only	List supported workflows and current model versions via GET /v1/workflows
`score_batch`read-only	Score up to 25 workflow items sequentially in one request via POST /v1/score/batch
`score_workflow`read-only	Score Sentinel healthcare workflows via POST /v1/score
`submit_feedback`	Submit structured claims outcome feedback via POST /v1/feedback
`validate_workflow_payload`read-only	Validate and normalize a workflow payload without consuming a scoring call via POST /v1/workflows/{workflow}/validate

Schemas: list_tools.

Similar MCP servers

More from io.sentinelsignal

Official server.json

{
  "name": "io.sentinelsignal/scoring",
  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
  "remotes": [
    {
      "url": "https://mcp.sentinelsignal.io/mcp",
      "type": "streamable-http",
      "headers": [
        {
          "name": "x-sentinel-api-key",
          "isSecret": true,
          "description": "Optional Sentinel API key for dedicated usage."
        }
      ]
    }
  ],
  "version": "0.1.6",
  "description": "Hosted MCP for denial, prior auth, reimbursement, workflow validation, batch scoring, and feedback."
}