# Contact and address book APIs for AI agents

> 3 contacts & address books ranked by the Anchor benchmark. Leader Google People API (B). APIs that read and update a person's own contacts and address book, search people they know and keep contact records in sync across accounts. Compared on read and write coverage, search, sync tokens, OAuth scopes and limits.

- Canonical: https://www.anchorterminal.com/categories/contacts
- Markdown: https://www.anchorterminal.com/categories/contacts.md (~1,500 tokens)
- Slim: https://www.anchorterminal.com/categories/contacts.min.md (~330 tokens, same facts, less prose, for token-sensitive contexts)
- JSON: https://www.anchorterminal.com/categories/contacts.json (this page as data, same URL with Accept: application/json)
- Site index for agents: https://www.anchorterminal.com/llms.txt (full text: https://www.anchorterminal.com/llms-full.txt)
- API: https://www.anchorterminal.com/api/v1/index.json
- Updated: 2026-10-14

APIs that read and update a person's own contacts and address book, search people they know and keep contact records in sync across accounts. Compared on read and write coverage, search, sync tokens, OAuth scopes and limits.

- Tools ranked: 3 · agent-ready (BB or better): 0 · accept x402: 0 · hosted endpoints: 3 · desk reviews by the panel: 0
- JSON: https://www.anchorterminal.com/api/v1/tools.json (list) · https://www.anchorterminal.com/api/v1/rankings.json (ranked) · https://www.anchorterminal.com/api/v1/x402.json (payable) · https://www.anchorterminal.com/api/v1/capabilities.json (by capability)
- Grades run AA, A, BB, B, C, D, E, F · methodology: https://www.anchorterminal.com/benchmark/

- Head-to-head comparisons (3): https://www.anchorterminal.com/compare/contacts/index.md
- Capabilities in this category: contacts.read, contacts.write, contacts.search, contacts.sync, contacts.groups
- https://letme.dev/contacts.read picks the top-graded tool in this list and says how to call it direct; calling through letme comes later (https://www.anchorterminal.com/letme/index.md)

## Ranking

| # | Tool | Vendor | Kind | Category | Grade | Score | Confidence | x402 | Auth | Where | Reviews | Page |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| 346 | Google People API | Google | HTTP API | Contacts | B | 65.2 | medium | no | OAuth | hosted | none | https://www.anchorterminal.com/tools/google-people-api.md |
| 369 | Microsoft Graph People and Contacts API | Microsoft | HTTP API | Contacts | B | 64.6 | medium | no | OAuth | hosted | none | https://www.anchorterminal.com/tools/microsoft-graph-people.md |
| 966 | ContactsPlus | Contacts Plus LLC | HTTP API | Contacts | E | 42.4 | medium | no | OAuth | hosted | none | https://www.anchorterminal.com/tools/contactsplus.md |

Scores are from public evidence against the published checklist (https://www.anchorterminal.com/benchmark/), with Performance and Task success pending. p95 latency and context cost come from our probes, which haven't run yet.

## Summaries

### 346. Google People API, B (65.2)

Google's REST API for a user's Google Contacts, contact groups, "Other contacts" and Workspace directory profiles, with incremental sync tokens and a read-only remote MCP server in developer preview. Covers saved contacts, contact groups, "Other contacts" and the Workspace directory under 12 OAuth scopes, with seven-day sync tokens and a read-only MCP server that warns against prompt injection. No status page covers it, quota numbers are only in the Cloud console, and searches need a warmup call first.

- Page: https://www.anchorterminal.com/tools/google-people-api · Markdown: https://www.anchorterminal.com/tools/google-people-api.md · JSON: https://www.anchorterminal.com/api/v1/tools/google-people-api.json
- Capabilities: contacts.read, contacts.write, contacts.search, contacts.sync, contacts.groups · endpoint: `https://people.googleapis.com/v1`

### 369. Microsoft Graph People and Contacts API, B (64.6)

Microsoft Graph endpoints for a user's Outlook personal contacts and contact folders, with delta sync, and the people API, which ranks the people most relevant to a user and supports fuzzy search. Covers Outlook personal contacts with delta sync and a people API that ranks the people a user works with and supports fuzzy search, all under separate read and write permissions. Contact creates have no idempotency key, the status page needs JavaScript, and Microsoft has no current MCP server for contacts.

- Page: https://www.anchorterminal.com/tools/microsoft-graph-people · Markdown: https://www.anchorterminal.com/tools/microsoft-graph-people.md · JSON: https://www.anchorterminal.com/api/v1/tools/microsoft-graph-people.json
- Capabilities: contacts.read, contacts.write, contacts.search, contacts.sync · endpoint: `https://graph.microsoft.com/v1.0`

### 966. ContactsPlus, E (42.4)

ContactsPlus (Contacts+) is a contact manager that syncs, deduplicates and enriches address books across Google, iCloud and Outlook. Agents reach it through an OAuth REST Contacts API with webhooks and a remote MCP server for Premium users. An address book that already merges Google, iCloud and Outlook contacts, reachable through OAuth scopes split by read and write and an MCP server that cannot delete or export and holds edits for the owner's approval. The REST reference has no rate limits, error codes or changelog, and its client libraries were archived in 2023.

- Page: https://www.anchorterminal.com/tools/contactsplus · Markdown: https://www.anchorterminal.com/tools/contactsplus.md · JSON: https://www.anchorterminal.com/api/v1/tools/contactsplus.json
- Capabilities: contacts.read, contacts.write, contacts.search, contacts.sync, contacts.groups · endpoint: `https://api.contactsplus.com/api/v1`

## How we test this category

In this run, public evidence against the published checklist. When the task suites run, one test account's contacts read, searched, created, updated and deleted through each listing's API, then synced after a change made elsewhere. We check field coverage, incremental sync, scopes and error handling. This test hasn't run yet, so Task success is pending and the grades here come from the categories assessed from public evidence.