Skip to main content
Glama
serve7-mcp-connectors

serve7-mcp-connectors

by MilosJova

Serve7 MCP Connector Library

Reusable MCP tools for Amazon Connect AI Agents and Bedrock AgentCore. Seven generic connectors — customer lookup, create a support ticket, check ticket status, schedule an appointment, update a CRM record, retrieve knowledge, and create a task — built once here, then reused across every Serve7 customer engagement instead of being wired up from scratch per project.

This is project #6 from the Fall 2026 co-op idea list ("Serve7 MCP Connector Library"). It's a working first version: every connector runs end to end today against an in-memory mock backend (no AWS account, no live CRM, no credentials needed to try it), with a clean seam for swapping in a real backend later.

Why an adapter, not a direct integration

Every connector's business logic (schema validation, what counts as an error, what fields go in and out) lives in src/connectors/*.ts and never talks to a concrete backend SDK directly. Instead it calls one of five small interfaces in src/adapters/types.ts — CrmAdapter, TicketingAdapter, SchedulingAdapter, KnowledgeAdapter, TaskAdapter. Today those are all implemented in-memory (src/adapters/mock.ts). Tomorrow, connecting a real Salesforce/ServiceNow/Connect-Cases/Bedrock-Knowledge-Base backend means writing one new adapter class and flipping one switch statement (src/adapters/index.ts) — zero changes to the connector code, its tests, or the MCP tool definitions an agent sees. See docs/adding-a-real-adapter.md.

MCP client (Claude Desktop, Bedrock AgentCore, ...)
        │  tool call: customer_lookup({ customerId: "cust-1001" })
        ▼
src/server.ts (stdio) or src/http-server.ts (deployed)
        │  registers every connector as an MCP tool
        ▼
src/connectors/customer-lookup.ts
        │  validates input (zod), calls adapters.crm.lookupCustomer(...)
        ▼
src/adapters/index.ts  →  mock.ts today, a real adapter later

Related MCP server: CRM Agent Tools

Project layout

src/
  connectors/       one file per MCP tool — schema + business logic only
  adapters/          the CRM/ticketing/scheduling/knowledge/task interfaces,
                      plus the in-memory mock implementations
  mock-data/         seed data the mock adapters serve
  mcp-server-factory.ts   registers every connector on an McpServer instance
  server.ts          stdio entrypoint (local dev, Claude Desktop, Claude Code)
  http-server.ts      Streamable-HTTP entrypoint (deployed, e.g. behind Lambda)
tests/               one test file per connector + a registry sanity test
deploy/              Dockerfile + AWS SAM template for a Lambda deployment
docs/                per-connector reference + how to add a real adapter

Running it locally

npm install
npm test              # 29 tests, all against the mock adapters
npm run typecheck      # strict TypeScript, zero `any` in connector code
npm start              # stdio MCP server — Ctrl+C to stop
npm run start:http      # HTTP MCP server on :8080 (curl http://localhost:8080/health)
npm run smoke           # real MCP client over stdio, calls all 7 tools end to end
npm run smoke:http      # same, over HTTP — start:http must be running first

Wiring it into Claude Desktop / Claude Code

Point an MCP client at the stdio server, e.g. in Claude Desktop's claude_desktop_config.json:

{
  "mcpServers": {
    "serve7-connectors": {
      "command": "npx",
      "args": ["tsx", "/absolute/path/to/serve7-mcp-connectors/src/server.ts"]
    }
  }
}

Then ask it something like "look up customer cust-1001" or "what knowledge articles do we have on emergency close announcements?" — it'll call customer_lookup / retrieve_knowledge against the mock data.

Deploying it for real use (e.g. from Bedrock AgentCore)

See deploy/README.md — builds a container-image Lambda behind an IAM-authenticated Function URL via sam deploy.

Adding an 8th connector

  1. Create src/connectors/my-new-tool.ts using defineConnector() — copy the shape of an existing one, e.g. create-task.ts.

  2. Add it to the CONNECTORS array in src/connectors/index.ts.

  3. Add a test file in tests/.

  4. Document it in docs/connectors.md.

server.ts, http-server.ts, and the registry test all pick it up automatically — nothing else to touch.

What's deliberately out of scope for this first version

Per the original project brief, each connector should eventually also cover authentication approach (done, at the adapter layer), a deployment template (done, deploy/), and documentation (done, docs/) — all shipped. Not yet built, and worth a fast-follow: a real adapter for at least one backend (so this stops being all-mock), and wiring a live Bedrock AgentCore agent to call it over the deployed HTTP endpoint end to end.

Available Tools

7 tools
create_support_ticketCreate Support TicketA

File a new support ticket for a customer when their issue can't be resolved in the current interaction. Use retrieve_status afterward to check progress on a ticket already created.

Inputs: subject (required), customerId (required), description (required), priority.

create_taskCreate TaskA

Create a follow-up task for a human teammate — e.g. 'call customer back with a refund confirmation' — when something needs manual handling after the AI-driven part of the interaction ends.

Inputs: title (required), assignee (required), description (required), dueDate.

customer_lookupCustomer LookupA

Look up a customer record by customer ID, email, or phone number. Returns account status and tier so an agent (human or AI) can personalize the interaction. Call this first in nearly every flow.

Inputs: email, phone, customerId.

retrieve_knowledgeRetrieve KnowledgeA

Search the knowledge base for articles relevant to a customer's question. Returns the top matches with a relevance score and source URL so responses can be grounded and cited.

Inputs: query (required), topK.

retrieve_statusRetrieve Ticket StatusA

Check the current status of a previously created support ticket by its ticket ID. Use this before telling a customer their issue is still 'in progress' vs resolved.

Inputs: ticketId (required).

schedule_appointmentSchedule AppointmentB

Book an appointment (call-back, in-branch visit, technician visit, etc.) for an existing customer.

Inputs: startTime (required), customerId (required), serviceType (required), durationMinutes.

update_crm_recordUpdate CRM RecordA

Patch fields on an existing customer's CRM record (e.g. after verifying a new phone number or email during a call). Only include the fields you want changed.

Inputs: customerId (required), tier, email, phone, +1 more.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A3.8/5.0

    Scored across 7 tools

    Disambiguation5/5

    Each tool targets a clearly distinct resource and action: customer lookup, ticket creation/status, appointment scheduling, CRM patching, knowledge search, and task creation. There is no meaningful overlap or ambiguity between tool purposes.

    Naming Consistency4/5

    Most tools follow the verb_noun pattern (create_support_ticket, retrieve_status, schedule_appointment, update_crm_record, retrieve_knowledge, create_task). The exception is customer_lookup, which reverses the order to noun_verb, creating a minor consistency deviation.

    Tool Count5/5

    Seven tools is a well-scoped size for a customer support/CRM connector. Each tool covers a distinct workflow step, and none feel redundant or unnecessary.

    Completeness3/5

    The surface covers customer lookup, ticket creation and status, knowledge retrieval, and follow-up tasks, but ticket lifecycle is incomplete (no update or close) and appointment management lacks cancellation/rescheduling. These are notable gaps for a full customer support workflow.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers