Loading…
Manages credit risk scoring, scorecard models, deployments, and observability through the Calibr platform API.
Do not connect
The assessed surface is high-risk. Remediate the findings before connecting.
Scanned 1 month ago Due for re-check
A server can change after it's graded. Re-run the automated scan to refresh this report.
This grade is deterministic and reproducible: the same server surface always yields the same grade under a given algorithm version. It is a real automated assessment computed by the MCPGrade engine from what the probe actually observed — not a fabricated or opinion score. It is not a manual human pentest, so it can miss context-specific risks.
Every signal below was measured directly by the automated probe. The grade is derived only from evidence like this — nothing is assumed.
The calibr MCP server exposes 23 tools, focused primarily on communication capabilities. Its published description reads: "Manages credit risk scoring, scorecard models, deployments, and observability through the Calibr platform API". It communicates over Streamable HTTP using the 2025-06-18 protocol revision, and does not require authorization to connect. MCPGrade currently rates calibr D — the assessed surface is high-risk and should be remediated before use. Its most notable findings include "Data-exfiltration parameters" and "Tool input schema requests a secret". This report is a deterministic, reproducible automated assessment: the same observed surface always yields the same grade under a given algorithm version, and it is refreshed as new scans arrive and free to read — but it is not a substitute for a manual human security review. Always re-check calibr's advertised tools, transport security, and authorization posture before connecting an autonomous agent or sharing sensitive context with it.
Add calibr to an MCP client using the endpoint below. Review the grade and findings above before granting an autonomous agent access.
MCP endpoint
https://mcp.cali-br.com/mcpStreamable HTTP transport. This is the MCP endpoint, not a website — paste it into your MCP client server list rather than a browser.
Captured passively during the read-only scan. Click any value to find servers that match it.
The tools this server advertises via tools/list — names, purposes, and the parameters each accepts, exactly as enumerated read-only.
Score a single credit applicant using a Calibr scorecard deployment. Calls the Calibr credit risk API at api.cali-br.com. Returns credit score, risk grade, probability of default, and point breakdown
Score a batch of credit applicants (up to 1000) using a Calibr scorecard deployment in a single request. Calls the Calibr credit risk API at api.cali-br.com.
List all deployed credit risk scorecard models in the Calibr platform (api.cali-br.com). Returns model name, version, status, environment (production/staging), and deployer info. Use this to discover
Get full detail for a specific Calibr credit risk scorecard model including the complete spec with variable definitions, bins, weights, and WoE values. Use this to understand what input variables a mo
Deploy a Calibr credit risk scorecard model to production or staging. Requires the full scorecard spec JSON containing model definition, variables, bins, and weights. Returns the new model ID and depl
List all active Calibr credit risk scorecard deployments. Each deployment has a slug (e.g. dep_WAUM), a champion model, and optionally challenger models for A/B testing. Use this to find deployment sl
Get full detail for a Calibr deployment including champion model, challenger models, traffic split percentages, and shadow mode status. Use the deployment slug (e.g. dep_WAUM).
Get live scoring statistics for a Calibr deployment: total scores processed, average score, average latency, and recent scoring activity. Use the deployment slug (e.g. dep_WAUM).
Compare champion vs challenger model performance for a Calibr deployment. Shows score distributions, average scores, and key metrics to decide whether to promote the challenger.
Promote a challenger model to champion in a Calibr deployment. This replaces the current champion and deactivates all challengers. Requires admin permissions. This is a production-impacting action.
Rollback a Calibr deployment to its previous champion model. Use this if a recently promoted model is underperforming. Requires admin permissions.
Adjust the traffic split between champion and challenger models in a Calibr deployment. Set what percentage of scoring requests go to the challenger (0-100).
List all Calibr API keys for your organization. Shows key prefix, scopes (score, read, admin), environment (production/staging), and last used date. Full key values are never returned.
Create a new Calibr API key. Returns the full key value ONCE — store it securely as it cannot be retrieved again. Requires admin permissions.
Permanently revoke a Calibr API key. This cannot be undone — the key will immediately stop working. Requires admin permissions.
Rotate a Calibr API key — generates a new key value and invalidates the old one. Returns the new full key value ONCE. Requires admin permissions.
List all webhooks configured for your Calibr organization. Webhooks receive notifications for events like model deployments, promotions, and key changes.
Create a new Calibr webhook to receive notifications. Supported events: model.deployed, deployment.promoted, deployment.rolled_back, deployment.traffic_updated, key.created, key.revoked, key.rotated.
Delete a Calibr webhook. This cannot be undone.
Send a test event to a Calibr webhook endpoint to verify it is correctly receiving and processing events.
Get the current month Calibr API usage for your organization: total score count, batch count, batch record count, plan tier, usage limit, and overage costs.
Get historical Calibr API usage data across previous months. Shows scoring volumes and costs over time.
Get Calibr audit log entries for your organization. Tracks all actions: model deployments, promotions, rollbacks, key operations, and more. Supports filtering by action type and pagination.
Sorted worst-first. Each finding shows its severity, what it means, its OWASP MCP Top-10 mapping, and a recommended fix — the check id links to the exact methodology row that produced it.
tool: calibr_create_webhook
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
nt.promoted)"},"secret":{"type":"string","description":"Optional signiRecommendationRemove side-channel parameters; constrain tool inputs.
tool: calibr_create_webhook
The input schema declares a parameter that asks the caller to hand over a password, key, token, or other secret — a credential-harvest / token-passthrough risk. (Bare pagination `token` params are excluded.)
parameter "secret"RecommendationNever pass secrets as tool arguments; authenticate out-of-band and remove credential parameters from the schema.
tool: calibr_delete_webhook
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
parameter "webhook_id"RecommendationRemove side-channel parameters; constrain tool inputs.
tool: calibr_test_webhook
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
parameter "webhook_id"RecommendationRemove side-channel parameters; constrain tool inputs.
The server accepts tool enumeration (and likely invocation) with no authentication.
RecommendationRequire OAuth 2.1 authorization for any server exposing non-public tools.
tool: calibr_update_traffic
The server advertises open-world / broadly-scoped capabilities.
no annotations on write-capable tool "calibr_update_traffic"RecommendationScope tools to the minimum needed.
tool: calibr_create_api_key
The server advertises open-world / broadly-scoped capabilities.
no annotations on write-capable tool "calibr_create_api_key"RecommendationScope tools to the minimum needed.
tool: calibr_create_webhook
The server advertises open-world / broadly-scoped capabilities.
no annotations on write-capable tool "calibr_create_webhook"RecommendationScope tools to the minimum needed.
tool: calibr_delete_webhook
The server advertises open-world / broadly-scoped capabilities.
no annotations on write-capable tool "calibr_delete_webhook"RecommendationScope tools to the minimum needed.
tool: calibr_test_webhook
The server advertises open-world / broadly-scoped capabilities.
no annotations on write-capable tool "calibr_test_webhook"RecommendationScope tools to the minimum needed.
Financial data service providing fundamental information for 30,000+ listed companies across the US, Japan, and Korea, sourced directly from SEC, EDINET, and DART regulatory filings.
Search tours, attraction tickets, and holiday packages across 24 countries.
Agentic visitor analytics with five tools for CRO and session analysis.
52 paid x402 API endpoints for AI agents — crypto, data, DeFi, and market intelligence, settled on Base.
Access Vonage API documentation, code snippets, tutorials, and troubleshooting resources.