Sentinel Signal MCP
OfficialClick on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Sentinel Signal MCP Score this claim for denial risk"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Sentinel Signal MCP for Healthcare Claims Scoring
Hosted and local MCP access for healthcare claims workflow scoring, usage, limits, and feedback.
Hosted First
Hosted remote MCP endpoint:
https://mcp.sentinelsignal.io/mcpSmithery listing:
@sentinelsignal/scoring(https://server.smithery.ai/sentinelsignal/scoring)Free no-signup trial key:
POST https://token.sentinelsignal.io/v1/keys/trialLocal package:
uvx sentinel-signal-mcp
Related MCP server: Claim Pilot MCP Server
Quickstart (10 lines)
uvx sentinel-signal-mcp
export SENTINEL_BASE_URL="https://api.sentinelsignal.io"
export SENTINEL_TOKEN_BASE_URL="https://token.sentinelsignal.io"
# Optional: export SENTINEL_API_KEY="ss_live_or_test_api_key_here"
# If omitted, the MCP server auto-mints a trial keyHosted remote MCP endpoint (Streamable HTTP): https://mcp.sentinelsignal.io/mcp
Smithery hosted listing: @sentinelsignal/scoring (https://server.smithery.ai/sentinelsignal/scoring)
If your MCP client supports remote HTTP MCP, point it at that URL and send Authorization: Bearer <SENTINEL_API_KEY>. For Smithery-hosted connections, the key is forwarded as x-sentinel-api-key.
Claude Desktop (drop-in MCP config)
{
"mcpServers": {
"sentinel-signal": {
"command": "uvx",
"args": ["sentinel-signal-mcp"],
"env": {
"SENTINEL_BASE_URL": "https://api.sentinelsignal.io",
"SENTINEL_TOKEN_BASE_URL": "https://token.sentinelsignal.io"
}
}
}
}Cursor (same MCP config shape)
{
"mcpServers": {
"sentinel-signal": {
"command": "uvx",
"args": ["sentinel-signal-mcp"],
"env": {
"SENTINEL_BASE_URL": "https://api.sentinelsignal.io",
"SENTINEL_TOKEN_BASE_URL": "https://token.sentinelsignal.io"
}
}
}
}Windsurf can use the same mcpServers block shape.
This package provides a local stdio MCP server, while the hosted remote service exposes the same healthcare claims tools over Streamable HTTP. It supports either:
PyPI: https://pypi.org/project/sentinel-signal-mcp/
a user-provided
SENTINEL_API_KEY, orautomatic no-signup trial key minting (
POST /v1/keys/trial) with secure local credential caching
Skills (MCP Tools)
list_workflows— list supported workflows and current model versionsget_workflow_schema— fetch required fields, optional fields, and an example payload for a workflowvalidate_workflow_payload— validate and normalize a workflow payload before scoringscore_workflow— score denial risk, prior auth, and reimbursement payloads against a named workflowscore_batch— score up to 25 workflow items in one requestget_limits— retrieve plan limits for the current keyget_usage— retrieve usage for a given monthsubmit_feedback— submit structured outcome feedback
Quick start (uvx)
Install
uv(if needed): https://docs.astral.sh/uv/Set env vars (optional
SENTINEL_API_KEY; if omitted, the server auto-mints a trial key and caches it):
export SENTINEL_BASE_URL="https://api.sentinelsignal.io" # optional (default shown)
export SENTINEL_TOKEN_BASE_URL="https://token.sentinelsignal.io" # optional (default shown)
# export SENTINEL_API_KEY="ss_live_or_test_api_key_here" # optional
export SENTINEL_TIMEOUT_SECONDS="30" # optionalRun the MCP server:
uvx sentinel-signal-mcpDeliverable behavior: install tool -> (optionally set env vars) -> agent can call score_workflow.
If no API key is configured, the MCP server resolves credentials in this order:
SENTINEL_API_KEYenv varcached trial key (
~/.sentinel/credentials.jsonby default) if not expired and base URLs matchmint a new trial key from
POST {SENTINEL_TOKEN_BASE_URL}/v1/keys/trial
Disable auto-trial with SENTINEL_NO_TRIAL=1.
MCP client config snippets
Claude Desktop (macOS/Linux example)
Add this to your MCP config JSON (mcpServers section):
{
"mcpServers": {
"sentinel-signal": {
"command": "uvx",
"args": ["sentinel-signal-mcp"],
"env": {
"SENTINEL_BASE_URL": "https://api.sentinelsignal.io",
"SENTINEL_TOKEN_BASE_URL": "https://token.sentinelsignal.io",
"SENTINEL_API_KEY": "ss_live_or_test_api_key_here",
"SENTINEL_TIMEOUT_SECONDS": "30"
}
}
}
}Generic MCP stdio client
If your client accepts a command + args + env definition:
command:
uvxargs:
["sentinel-signal-mcp"]env:
optional
SENTINEL_API_KEY(if omitted, auto-trial mint is used unless disabled)optional
SENTINEL_BASE_URLoptional
SENTINEL_TOKEN_BASE_URLoptional
SENTINEL_CREDENTIALS_PATHoptional
SENTINEL_NO_TRIAL=1optional
SENTINEL_TIMEOUT_SECONDS
Tool details
list_workflows
Calls GET /v1/workflows so agents can discover the supported healthcare workflows and current model versions before scoring.
No arguments.
get_workflow_schema
Calls GET /v1/workflows/{workflow}/schema so agents can fetch required fields, optional fields, enums, and example payloads before issuing a score.
Arguments:
workflow(str): workflow ID such ashealthcare.denial
validate_workflow_payload
Calls POST /v1/workflows/{workflow}/validate and returns normalized payload output plus structured validation issues without consuming a scoring call.
Arguments:
workflow(str): workflow ID such ashealthcare.denialpayload(object): workflow payload object to validate
score_workflow
Calls the Sentinel Signal unified scoring endpoint (POST /v1/score).
Arguments:
workflow(str): workflow ID (for examplehealthcare.denial,healthcare.prior_auth,healthcare.reimbursement)payload(object): workflow payload objectoptions(object, optional): scoring options object
Example MCP tool call input:
{
"workflow": "healthcare.denial",
"payload": {
"payer_id": 44,
"provider_id": 1021,
"patient_id": "PT_DEMO_001",
"patient_age": 57,
"patient_sex": "F",
"cpt_code": "99214",
"icd10_code": "M5450",
"service_date": "2026-02-13",
"place_of_service": "11",
"units": 1,
"billed_amount": 210.0,
"allowed_amount": 145.0,
"claim_frequency_code": "1",
"network_status": "in_network",
"prior_authorization_required": true,
"prior_authorization_on_file": false,
"referral_on_file": false,
"is_emergency": false,
"modifier_1": "25",
"submission_channel": "edi",
"data_source": "api"
},
"options": {
"allow_fallback": true,
"distribution_profile": "commercial_beta",
"operating_point": "high_recall"
}
}get_limits
Calls GET /v1/limits for the current API key.
No arguments.
get_usage
Calls GET /v1/usage.
Arguments:
month(str, optional): month filter (for example2026-02)
score_batch
Calls POST /v1/score/batch to score up to 25 workflow items sequentially in one request.
Arguments:
items(array): list of{workflow, payload, options?}scoring itemscontinue_on_error(bool, optional): whether later items should continue if an earlier item fails
submit_feedback
Calls POST /v1/feedback with a structured feedback payload.
Arguments:
feedback(object): rawFeedbackRequestobject
Example input:
{
"feedback": {
"request_id": "00000000-0000-0000-0000-000000000001",
"endpoint": "denial",
"observed_outcome": "denied",
"expected_outcome": "paid",
"confidence_mismatch": true,
"payer_id": 44,
"cpt": "99214",
"denial_reason_code": "AUTH_MISSING",
"severity": "med",
"days_to_outcome": 12,
"notes": "Example feedback payload for agent integration testing."
}
}Trial key caching (auto-mint mode)
Default cache path:
~/.sentinel/credentials.json(permissions0600)
Cached payload includes the trial key plus metadata used by the agent/runtime:
{
"api_key": "ss_trial_...",
"account_id": "uuid",
"expires_at": "2026-03-10T00:00:00Z",
"limits": {
"monthly_quota": 1000,
"rps": 1,
"burst": 5
},
"upgrade_url": "https://sentinelsignal.io/portal/dashboard",
"token_base_url": "https://token.sentinelsignal.io",
"api_base_url": "https://api.sentinelsignal.io"
}The MCP server stores both base URLs in the cache so it does not accidentally reuse a trial key across different environments.
Reset the cached credentials (force a fresh trial key next run):
uvx sentinel-signal-mcp --reset-credentialsEnvironment variables
SENTINEL_BASE_URL(optional, defaulthttps://api.sentinelsignal.io): scoring API base URLSENTINEL_TOKEN_BASE_URL(optional, defaulthttps://token.sentinelsignal.io): token-service base URL used for trial key mintingSENTINEL_API_KEY(optional): if set, used directly and never cachedSENTINEL_CREDENTIALS_PATH(optional, default~/.sentinel/credentials.json)SENTINEL_NO_TRIAL(optional): set to1to disable auto-trial mintingSENTINEL_TIMEOUT_SECONDS(optional, default30)SENTINEL_API_BASE_URL(legacy alias forSENTINEL_BASE_URL)
Error behavior for agents
The MCP tools return structured payloads for both success and common operational failures:
success ->
{"ok": true, ...}quota exhausted / payment required (
402) ->{"ok": false, "error": {"action": "upgrade_required", "upgrade_url": "...", ...}}rate limited (
429) ->{"ok": false, "error": {"action": "retry_later", ...}}auth/config issues (
401/403or missing credentials) ->{"ok": false, "error": {"action": "configure_credentials", ...}}
Publishing (Python / uvx path)
This package is set up for PyPI publishing so users can run it with:
uvx sentinel-signal-mcpTypical release commands:
python -m build
python -m twine upload dist/*Security notes
Do not commit real API keys or customer payloads.
Use placeholder values in client configs and examples.
Auto-minted trial credentials are cached locally with file permissions
0600.Use
SENTINEL_CREDENTIALS_PATH=/tmp/...for ephemeral environments if you do not want a persistent cache.
Available Tools
8 toolsget_limitsAInspect
Return plan limits for the current API key (GET /v1/limits).
Inputs: no named parameters. Returns: object
get_usageAInspect
Return usage for the current API key (GET /v1/usage). Optional month format: YYYY-MM.
Inputs: month. Returns: object
get_workflow_schemaBInspect
Fetch required fields, optional fields, and example payloads for a workflow (GET /v1/workflows/{workflow}/schema).
Inputs: workflow (required). Returns: object
list_workflowsAInspect
List supported workflows and current model versions (GET /v1/workflows).
Inputs: no named parameters. Returns: object
score_batchBInspect
Score up to 25 workflow items sequentially in one request (POST /v1/score/batch).
Inputs: items (required), continue_on_error. Returns: object
score_workflowCInspect
Call Sentinel Signal unified workflow scoring (POST /v1/score).
Inputs: payload (required), workflow (required), options. Returns: object
submit_feedbackBInspect
Submit structured feedback for a prior scoring request (POST /v1/feedback).
Inputs: feedback (required). Returns: object
validate_workflow_payloadAInspect
Validate and normalize a workflow payload without consuming a scoring call (POST /v1/workflows/{workflow}/validate).
Inputs: payload (required), workflow (required). Returns: object
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 8 tools
Tools are mostly distinct, but score_workflow and score_batch both deal with scoring and could be confused without careful reading of their descriptions. get_usage and get_limits are also related but easily differentiated.
All tool names follow a consistent lowercase verb_noun pattern (get_, score_, submit_, list_, validate_). This makes the set highly predictable.
With 8 tools, the server covers scoring (single and batch), validation, schema retrieval, workflow listing, feedback, usage, and limits. This is well-scoped for the API's purpose.
The tool surface covers the main lifecycle of workflow scoring: single/batch scoring, validation, schema, workflow list, feedback, and account info. A minor gap might be a tool to retrieve historical scoring results, but this is likely handled by the score responses themselves.
Maintenance
Related MCP Connectors
MCP server for VC pitch-deck scoring, thesis-fit matching, and deal-flow management.
Hosted MCP server for pre-action AI governance verdicts, model routing, and evidence verification.
41MCP server for CertScore.ai public website risk-signal workflows.
Evidence-readiness MCP server: validate, audit, and score briefs, memos, and evidence packs.
Related MCP Servers
- FlicenseNot gradedqualityCmaintenanceA comprehensive MCP server that bridges AI applications with FHIR healthcare data systems, enabling patient data access, clinical data retrieval, and data quality assessment.4-
- AlicenseNot gradedqualityDmaintenanceMCP server for insurance claim pilot tools, providing policy search, claim lookup, and fraud score calculation.MIT
- FlicenseAqualityDmaintenanceAn MCP server that reads a clinical note and returns ranked ICD-10-CM diagnosis code candidates with clinical reasoning, validated against official CMS coding constraints.2-
- FlicenseNot gradedqualityDmaintenanceMCP server that reviews insurance claims against policy documents, providing coverage decisions, policy clause retrieval, claim history lookup, coverage rule checks, and fraud risk scoring via four tools.-