Read and update AgencyBloc individuals, groups, policies and agents; log activities and notes. Hosted by usefulapi — connect from Claude, ChatGPT, Cursor, or any MCP client.
Team and Enterprise: an Owner adds the connector for the organization first.
Run this command, then run /mcp in Claude Code to log in:
Add to Cursor or add this to ~/.cursor/mcp.json:
{
"mcpServers": {
"agencybloc": {
"url": "https://agencybloc.usefulapi.io/mcp"
}
}
}Add to VS Code or add this to .vscode/mcp.json:
{
"servers": {
"agencybloc": {
"type": "http",
"url": "https://agencybloc.usefulapi.io/mcp"
}
}
}No Add custom MCP server option? It depends on your account or workspace settings: see OpenAI's guide.
Run these commands. The second one opens the login page:
Other MCP clients (Windsurf, Cline, Zed and more): add the URL as a remote MCP server (Streamable HTTP). The client then opens the login page in your browser. Do not add an Authorization header: see Before you connect.
The login page asks for your AgencyBloc API SID and AgencyBloc API key.
AgencyBloc support issues the SID and key (phone 866-338-7075, or ask in the help center); the API is a paid add-on of your AMS+ account. The key has full access to the account, so treat it like a password. Your credentials are used only to call the AgencyBloc API on your behalf; they are never shown to anyone. SSNs and other national ids are removed from everything this server returns.
Add only the URL. Do not add an Authorization header or an API key to the client config. The server signs you in with OAuth: the login page asks for your AgencyBloc API SID and AgencyBloc API key. If the config has such a header, remove it: some clients then send that header instead of the login token, and every call fails with 401.
Turn on the AgencyBloc connector, then ask in plain words. The AI picks the tools.
| Tool | Type | What it does |
|---|---|---|
agencybloc_search_individuals | read | Search individuals Search individuals (clients and contacts) in AgencyBloc. All filters are optional and combine; with none you get the first records. Returns id, name, email, birth date, phones and last-updated time (national ids such as SSN are never returned). Use updated_since to find recently changed people. POST individuals/search. |
agencybloc_get_individual | read | Get individual One individual by id, with addresses, policies and custom fields (and activities when include_activities is true). National ids are removed. POST individuals/detail. |
agencybloc_search_groups | read | Search groups Search groups (employer / business accounts) in AgencyBloc by name, type or phone. Returns id, name, type and phone. POST groups/search. |
agencybloc_get_group | read | Get group One group by id, with addresses, policies and custom fields (and activities when include_activities is true). POST groups/detail. |
agencybloc_search_policies | read | Search policies Search policies by number, coverage type, carrier, holder, servicing agent, application date or last update. Returns id, holder, policy number, carrier, status, coverage type, effective and renewal dates. Use submitted_after/updated_since for recent business. POST policies/search. |
agencybloc_get_policy | read | Get policy One policy by id: holder, agent, carrier, status, dates, premium, coverages and custom fields. POST policies/detail. |
agencybloc_search_agents | read | Search agents Search agents (producers) by name, email or phone. Returns id, name, email and phones. POST agents/search. |
agencybloc_get_agent | read | Get agent One agent by id, with agencies, addresses and custom fields (and activities when include_activities is true). POST agents/detail. |
agencybloc_search_carriers | read | Search carriers Search insurance carriers by name or phone. Returns id, name, abbreviation and phones. POST carriers/search. |
agencybloc_list_activities | read | List activities of a record All activities (tasks, calls, renewals) logged on one group, individual, agent, carrier or lead: date, subject, notes, status, type, method, priority and follow-up. There is no paging. POST activities/list. |
agencybloc_get_activities | read | Get activities by id Activities by id (1-50 ids), e.g. the ids shown on a policy or individual. POST activity/list. |
agencybloc_list_notes | read | List notes of a record Notes (subject, body, author, dates, pinned flag, attachment names) on one agent, group, individual or policy, newest change first. There is no paging. POST notes/list. |
agencybloc_search_leads_by_phone | read | Search sales records (leads) by phone Find Sales Enablement records (leads) by phone number; the search is by phone only. Only accounts with the Sales Enablement module have them. POST salesEnablement/leads/searchphone. |
agencybloc_get_lead | read | Get sales record (lead) One Sales Enablement record (lead) by record id. POST salesEnablement/Leads/detail. |
agencybloc_create_individual | write | Create individual WRITE: create a new individual (client or contact) in AgencyBloc. Needs first and last name; everything else is optional. It does not check for duplicates: search first. Returns the new individualID. POST individuals/create. |
agencybloc_update_individual | write | Update individual WRITE: change fields of an existing individual; fields you leave out are not sent. Tags are replaced (empty string clears them). Addresses are not changed here. Returns the individualID. POST individuals/update. |
agencybloc_create_group | write | Create group WRITE: create a new group (employer / business account) in AgencyBloc. It does not check for duplicates: search first. Returns the new groupID. POST groups/create. |
agencybloc_update_group | write | Update group WRITE: change fields of an existing group (including its name); fields you leave out are not sent. Returns the groupID. POST groups/update. |
agencybloc_create_policy | write | Create policy WRITE: create a policy on an existing group or individual. Needs the holder (entity_id + entity_type), coverage type, status and the carrier's full name; unknown coverage types / statuses are created in the account. Returns the new policyID. POST policies/create. |
agencybloc_update_policy | write | Update policy WRITE: change fields of an existing policy (status, carrier, dates, premium ...); fields you leave out are not sent. Returns the policyID. POST policies/update. |
agencybloc_create_activity | write | Create activity WRITE: log an activity (call, task, renewal reminder) on a group, individual, agent, carrier or lead. Status, type, method and priority are the text values of the account's dropdowns (My Agency Settings > Data Administration); unknown values are created. When the status is not Complete the activity is a follow-up: give follow_up_user_id and follow_up_date (and start/end times), and AgencyBloc assigns it to that user. Nothing is sent to the customer. Activities cannot be edited or deleted through the API. Returns the new activityID. POST activities/create. |
agencybloc_create_note | write | Add note WRITE: add one note (subject + body) to an agent, group, individual or policy. AgencyBloc never allows notes to be edited or deleted through the API (audit rule), so the note is permanent. Pinning a note unpins the previously pinned one. Returns the new note id. POST notes/create. |
agencybloc_usage_status | Usage status (free-tier meter) Report the caller's current usage: the plan, calls used this month, the limit of the plan (the free monthly cap or the Pro fair use limit), remaining, and whether the limit is reached. Read-only; does not count against the meter. | |
agencybloc_request_feature | Request a missing feature Tell usefulapi that the user needs something the AgencyBloc tools cannot do yet (a missing tool, field or filter). Call it only when the user asks for something none of the tools can do, and tell the user that you send the request. Do not call it for errors or for normal requests. Do not include personal data, credentials or customer records. Stored with the product name and the client type (for example Claude or Cursor), without the user's account. At most 5 requests per day. Does not count against the meter. | |
agencybloc_upgrade | Upgrade to Pro (unlimited*) Get Pro: unlimited tool calls (fair use limit: 10,000 a month) on AgencyBloc (the free tier caps monthly usage). Plans: "monthly" — $9/month; "yearly" — $90/year (2 months free). Cancel any time: Pro then runs to the end of the paid period, so it also suits a one-time job. *A fair use limit applies. For heavy use (near Pro's limit): "plus" or "plus_yearly" — Pro+, $19/month or $190/year, unlimited tool calls (fair use limit: 100,000 a month); an existing Pro subscription changes to Pro+ in place (needs confirm: true; the price difference for the rest of the period is charged at once). Otherwise returns a short link to open in your browser (it opens Stripe Checkout); after payment the account upgrades automatically. Does not count against the meter. | |
agencybloc_cancel_subscription | Cancel the Pro subscription Cancel the caller's AgencyBloc Pro subscription at the end of the paid period (no refund for the current period; Pro continues until then, then the free tier applies). Requires confirm: true. Run agencybloc_upgrade later to undo the cancel before the period ends. Does not count against the meter. |
| Plan | Price | Limit |
|---|---|---|
| Free | $0 | 50 tool calls / month |
| Proper user | $9/mo · $90/yr | Unlimited* |
*Pro fair use limit: 10,000 tool calls a month on this server. For more, write to [email protected].
Pro covers this AgencyBloc server only. Subscribe with agencybloc_upgrade (it returns a Stripe Checkout link). Cancel any time with agencybloc_cancel_subscription: Pro continues to the end of the paid period, with no refund for the current period, and running agencybloc_upgrade before then undoes the cancel. Or write to [email protected].
No. usefulapi is an independent service. It is not affiliated with or endorsed by AgencyBloc. The server calls the AgencyBloc API with your own AgencyBloc access, so it sees only the data that your account can see.
Yes. In Claude, add this server's URL as a custom connector. In ChatGPT, add it as a custom MCP server in Plugins. Then log in once. Cursor, VS Code, Claude Code and Codex work too. See the setup steps.
The login page asks for your AgencyBloc API SID and AgencyBloc API key. See Before you connect for where to find them.
No. Add only the URL. Do not add an Authorization header or an API key to the client config. The server signs you in with OAuth: the login page asks for your AgencyBloc API SID and AgencyBloc API key. If the config has such a header, remove it: some clients then send that header instead of the login token, and every call fails with 401.
The login stores them encrypted in the authorization grant of your connection. The server uses them to call the AgencyBloc API for you and to derive a private account id for usage metering. usefulapi does not show them on any page or in any reply. To stop all access, remove the connector and change or delete these credentials in AgencyBloc.
Yes, if you approve it. 8 of the 22 AgencyBloc tools can create or change data. The other 14 are marked read-only. Most MCP clients ask you to approve a tool call before it runs.
The Free plan gives 50 tool calls / month. Pro costs $9/mo or $90/yr, with unlimited tool calls (fair use limit: 10,000 tool calls a month), for this AgencyBloc server only. Cancel any time: Pro then runs to the end of the paid period. Run agencybloc_usage_status to see how many calls you used.
Ask the AI to run agencybloc_upgrade: it returns a Stripe Checkout link. To cancel, run agencybloc_cancel_subscription. Pro continues to the end of the paid period.
Tell the AI what you wanted to do. It can send the request with agencybloc_request_feature. We store the text with the server name, the type of AI client and the tool you tried, not with your account, and read every request when we plan new tools. You can send up to 5 requests per day.
Any client that supports remote MCP servers (Streamable HTTP) with OAuth login: Claude (web and desktop), Claude Code, ChatGPT, Codex, Cursor, VS Code, Windsurf and others.
This is a Model Context Protocol endpoint — meant to be connected from an AI client, not opened in a browser. An invalid_token response at the URL is the auth gate working as designed; clients authenticate automatically.