ScamCallID

ScamCallID — connector documentation

• MCP endpoint: https://scamcallid.connectorbay.com/mcp
• REST API: POST https://scamcallid.connectorbay.com/v1/tools/{tool_name}, described by the OpenAPI 3.1 spec at https://scamcallid.connectorbay.com/openapi.json
• Transport: Streamable HTTP, stateless, MCP specification 2025-06-18 or later
• Authentication: none required. An optional Authorization: Bearer <key> raises rate limits.
• Health: https://scamcallid.connectorbay.com/health · Tool schemas: https://scamcallid.connectorbay.com/tools.json
• Publisher: Unify Dynamics LLC · connectorbay.com/scamcallid · agent@connectorbay.com

What ScamCallID is for

A call comes in claiming to be the IRS, your bank, or a grandchild in trouble, and you need to know — right now — whether the tactics being used match a known scam pattern, and how to actually verify who's calling. ScamCallID answers that from one hand-curated reference of common scam-call patterns.

ScamCallID does not look up, identify, or trace real phone numbers. It is a companion to a phone-lookup app's EDUCATIONAL side — teaching the tactics scam calls use — not a replacement for a number-lookup service, and it can never tell you who actually called you.

What it does

list_scam_patterns gives the full catalog of common scam-call patterns. get_scam_pattern returns full detail on one pattern by name or natural-language description — government/IRS impersonation, tech-support scam, grandparent/family-emergency scam, prize/lottery scam, extended-car-warranty robocall, or one-ring/ Wangiri callback scam — including how it works, its tell-tale signs, what the scammer is actually after, and a reality-check fact about how the real organization operates. verification_methodology explains the single most reliable way to check whether a call claiming to be from an organization is real: hang up, then contact the organization yourself using a number or channel you already trust, never one the caller gave you, since caller ID can be spoofed. score_call_risk takes a set of described call characteristics (unsolicited call, claimed government/bank/tech identity, manufactured urgency, threats, a request for gift cards/wire/crypto, a request to stay on the line or keep it secret, a request for remote computer access, a request to "verify" personal or account info) and computes a real weighted red-flags score out of 100, a risk tier, and which flags matched and why each one matters. risk_flag_reference lists every flag score_call_risk accepts.

Every pattern in ScamCallID's dataset was checked against widely published public consumer-fraud guidance from the Federal Trade Commission (FTC), the Federal Communications Commission (FCC), and the AARP Fraud Watch Network before being written into the reference data.

What it is not

ScamCallID is not a phone-number lookup or caller-ID service — it never receives, stores, or attempts to identify an actual phone number, and it cannot tell you who called you. It is not a fraud-investigation or law-enforcement tool — score_call_risk describes how closely a described call matches known scam tactics, which is a pattern match, not a verdict, and a low score never proves a call is legitimate any more than a high score proves it's a scam. And it is never a substitute for independent verification — for any call asking for money, payment codes, remote computer access, or personal information, verify independently using verification_methodology before doing anything the caller asked.

Tools

Pattern catalog

list_scam_patterns — The full catalog of common scam-call patterns this reference covers, each with a one-line summary of how it works. Use for "what kinds of phone scams are there".

get_scam_pattern — Full detail on one scam-call pattern: how it works, its tell-tale signs, what the scammer is actually after, and a reality-check fact about how the real organization operates. Use for "someone called claiming to be the IRS", "what's a grandparent scam". Args: pattern.

Verification

verification_methodology — The single most reliable method for checking whether a call claiming to be from an organization is real: hang up, then contact the organization yourself using a number or channel you already trust — never one the caller gave you, since caller ID can be spoofed. Use for "how do I know if this call from my bank is real".

Risk scoring

score_call_risk — A computed red-flags risk score (0-100) from user-described call characteristics, with a risk tier and an explanation of which flags matched and why. Scores a described call, never a real phone number. Use for "score this call: they asked for gift cards and threatened arrest". Args: 8 boolean flags (see risk_flag_reference).

risk_flag_reference — Every flag score_call_risk accepts, with its scoring weight and why it matters.

Conventions

• Read-only. Every tool reads bundled reference data or computes from arguments; nothing is written anywhere and nothing about the user is stored.
• Result envelope. ok: true with data, or ok: false with a structured error (bad_input). Every response carries the no-real-lookup attribution.
• Rate limits. Free tier 60 tool calls/minute and 300/day per user (keyed on the user identifier supplied by the host agent, else client IP); Pro keys raise this. Over-limit calls return HTTP 429 with Retry-After. initialize and tools/list are never counted.

Support

agent@connectorbay.com · connectorbay.com/scamcallid/support

ScamCallID — Privacy Policy

Effective 28 September 2026. Unify Dynamics LLC ("we", "us"), Menlo Park, California.

What ScamCallID is. ScamCallID is a connector (an MCP server and REST API) that AI assistants and personal agents call on your behalf for scam-call pattern-recognition education: a catalog of common scam-call patterns, an independent-verification methodology, and a computed red-flags risk score from a described call. You interact with your assistant; the assistant sends us only the arguments needed for that one lookup or calculation.

ScamCallID never performs a real phone-number lookup. It does not accept, process, retain, or attempt to identify an actual telephone number, caller ID value, or call record. score_call_risk takes only boolean descriptions of a call's characteristics (for example, "asked for gift cards: yes/no") — never a phone number, recording, or transcript of the actual call.

What we receive. The arguments of each tool call — for example, a pattern name like "irs scam" or a set of boolean call characteristics — the technical headers needed to serve the request (an IP address or a client identifier supplied by the assistant, and a Pro API key if you have one), and standard server logs.

Everything is answered from a bundled reference file or computed from your arguments, and nothing is stored. No request is forwarded to any third party — there is no upstream call at all — and no query is logged in request bodies, recorded, or used to train anything. Each request is answered independently and nothing carries over between requests; ScamCallID does not build a profile of who has called you or what scams you've encountered.

What we do not receive or store. We do not receive your conversation with the assistant, your name, an actual phone number, or a recording or transcript of any call. Rate-limit counters (a client identifier and timestamps) are held in memory for at most 24 hours. Hosting-provider access logs, which contain IP addresses and request paths but not request bodies, are retained for up to 30 days for security and abuse prevention.

Sub-processors. None — the entire dataset is bundled with the server and every response is computed locally. Hosting: Vercel (United States regions).

Legal bases and your rights. Our processing is necessary to provide the service you request through your assistant. Because we store no personal data beyond short-lived logs, requests to access, correct, or delete personal data are usually satisfied automatically; you can still contact agent@connectorbay.com and we will respond within 30 days. We do not sell or share personal information and do not use your data to train models.

Not a fraud-reporting or law-enforcement channel. If you have been the victim of a scam call, report it to the Federal Trade Commission at reportfraud.ftc.gov and, for unwanted or illegal robocalls, to the FCC at fcc.gov/complaints — ScamCallID does not file reports on your behalf and is not a substitute for doing so.

Changes. We will post changes here with a new effective date.

ScamCallID — Terms of Service

Effective 28 September 2026. These terms govern use of the ScamCallID connector ("the Service") operated by Unify Dynamics LLC ("we", "us").

1. The Service. ScamCallID returns hand-curated scam-call pattern-recognition REFERENCE and EDUCATION — common scam-call patterns, tell-tale signs, a verification methodology, and a computed red-flags risk score from described call characteristics — from data bundled with the server. It is accessed through an AI assistant or directly over MCP or HTTP.
2. Not a phone-number lookup, caller-ID, or number-identification service. ScamCallID does NOT look up, identify, trace, or verify a real telephone number, and it never claims to tell you who actually called you. It is a companion to a phone-lookup app's educational side, not a replacement for one.
3. Not a fraud-investigation, law-enforcement, or legal tool. score_call_risk scores how closely a described call matches widely reported scam tactics. This is a pattern match against general education, not a verdict, an accusation, or evidence of any individual's or organization's conduct. A low score never proves a call is legitimate, and a high score is not proof of a crime.
4. Verify independently before acting. For any call asking for payment, payment codes, remote computer access, or personal or account information, verify independently — using a number or channel you already trust, never one the caller provided — before doing anything the caller asked. Do not rely on this Service in place of your own judgment or independent verification.
5. Individual results vary. Real scam calls vary in wording and tactics, and new patterns emerge constantly. The patterns and scoring here are widely reported starting points, not an exhaustive list, and they can never account for every possible scam call.
6. Acceptable use. Automated use within the published rate limits is welcome. Do not represent ScamCallID's output as a caller-identification result, a fraud determination, or legal advice to any third party.
7. Availability. The Service is provided "as is" without warranty of any kind. We may change, limit, or discontinue it at any time.
8. Data. Our Privacy Policy describes what we process. In short: your query is answered from a bundled reference file or computed from your arguments, and nothing is stored. No real phone number is ever accepted or processed.
9. Pro keys. Optional Pro API keys are issued at our discretion, are personal to the holder, and may be revoked for abuse.
10. Liability. To the fullest extent permitted by law, Unify Dynamics LLC is not liable for any loss — including financial loss arising from a scam call — arising from use of or reliance on the Service in place of independent verification, professional advice, or a report to the appropriate authority. Our total liability is limited to US $100.
11. Governing law. California law; venue in San Mateo County, California.
12. Contact. Unify Dynamics LLC · agent@connectorbay.com · https://connectorbay.com/scamcallid

ScamCallID support

Email agent@connectorbay.com. We answer within two business days.

• MCP endpoint: https://scamcallid.connectorbay.com/mcp
• REST API: https://scamcallid.connectorbay.com/openapi.json
• Live status: https://scamcallid.connectorbay.com/health

When you report a problem, include the question you asked your agent, roughly when, and which agent you used (for example Claude, ChatGPT or Gemini). Never send us passwords, account numbers or ID numbers. ScamCallID never asks for them.