Pipeline CRM MCP server for AI agents

Live

BEARER TOKEN

CRM

CRM & Sales

Pipeline CRM gives your agent sales CRM work: create and update deals, people, and companies, log activities and comments, schedule tasks and events, summarize deals by stage, and manage projects and milestones.

  • Per-user credentials: each call uses the actual user's access token, never a shared bot.
  • Encrypted per-tenant vault: AES-256, resolved at request time, never in LLM context.
  • Scoped before every call: pre-call scope check, 90-day SIEM-exportable audit chain.
Pipeline CRM
agent · Acme Q3
Run
How much is in each pipeline stage right now?
S
pipelinecrm_deal_totals_by_stage_get
109ms
Sales agent
42 deals worth $1.3M across 6 stages. Proposal holds the most value at $480K across 9 deals.
Sources: Pipeline CRM, 6 stages
pipelinecrm
6 stages
18:29
Message Claude...

Tools your sales agent reaches for on Pipeline CRM, scoped per user.

CALL ANY TOOL
115 tools for sales in Pipeline CRM: create and update deals, people, and companies, log notes and comments, schedule tasks and events, run saved searches, and manage projects, milestones, and files.
pipelinecrm_audits_list
List audits
List the change history of records you can see, optionally filtered by record type and ID, user, change type, field or date. Returns a page of audit entries (id, auditable_type, auditable_id, user_id, audit_type, model_column, value before and after, created_at) plus pagination. Use it to see who changed what on a deal, person or company.
Parameters
Name
Type
Required
Description
added_from
string
Optional
Only return records whose change date is on or after this date (YYYY-MM-DD, user's time zone). Example: 2026-01-01
added_to
string
Optional
Only return records whose change date is on or before this date (YYYY-MM-DD, user's time zone). Example: 2026-03-31
audit_type
string
Optional
Only return this kind of change, such as create, update or destroy. Example: update
auditable_ids
string
Optional
Only return changes to these record IDs. One ID or a comma-separated list. Example: 4521
auditable_type
string
Optional
Only return changes to this record type, such as Deal, Person or Company. Example: Deal
model_column
string
Optional
Only return changes to this field name. Example: deal_stage_id
page
integer
Optional
Page number to return, starting at 1. Default 1. Example: 1
per_page
integer
Optional
Number of records per page, at most 200. Default 200. Example: 50
sort
string
Optional
Sort key, `-` prefix for descending. Example: -created_at
user_ids
string
Optional
Only return changes made by these users. One ID or a comma-separated list. Example: 13
pipelinecrm_calendar_entry_create
Create calendar entry
pipelinecrm_calendar_entry_delete
Delete calendar entry
pipelinecrm_calendar_entry_get
Get calendar entry
pipelinecrm_calendar_entry_update
Update calendar entry
pipelinecrm_call_dispositions_list
List call dispositions
pipelinecrm_companies_autocomplete
Companies autocomplete
pipelinecrm_company_child_add
Add company child
pipelinecrm_company_child_remove
Remove company child
pipelinecrm_company_children_list
List company children
pipelinecrm_contact_tags_list
List contact tags
pipelinecrm_deal_create
Create deal
pipelinecrm_deal_delete
Delete deal
pipelinecrm_deal_get
Get deal
pipelinecrm_deal_loss_reasons_list
List deal loss reasons
pipelinecrm_deal_tags_list
List deal tags
pipelinecrm_deal_update
Update deal
pipelinecrm_documents_list
List documents
pipelinecrm_message_templates_list
List message templates
pipelinecrm_note_comment_get
Get note comment
pipelinecrm_people_list
List people
pipelinecrm_person_create
Create person
pipelinecrm_person_delete
Delete person
pipelinecrm_person_get
Get person
pipelinecrm_person_notes_list
List person notes
pipelinecrm_person_update
Update person
pipelinecrm_project_archive
Archive project
pipelinecrm_project_templates_list
List project templates
pipelinecrm_search_get
Get search
pipelinecrm_starred_searches_list
List starred searches

For more tools, view docs.

Build your Agent
Same auth pattern across LangChain, OpenAI, Anthropic, and Google ADK.
Python · LlamaIndex
import { ScalekitClient } from "@scalekit-sdk/node";
import { createReactAgent } from "@langchain/langgraph/prebuilt";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);

// Pipeline CRM tools scoped to this user
const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["pipelinecrm"], toolNames: [
    "pipelinecrm_deals_list",
    "pipelinecrm_note_create",
    "pipelinecrm_calendar_entry_create"] },
  pageSize: 100,
});

const agent = createReactAgent({ llm, tools });
await agent.invoke({ messages: [{ role: "user", content: "Log a call note on the Contoso deal and schedule a follow-up task" }] });
import OpenAI from "openai";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);
const openai = new OpenAI();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["pipelinecrm"] }, pageSize: 100,
});

const res = await openai.chat.completions.create({
  model: "gpt-5",
  messages: [{ role: "user", content: "Log a call note on the Contoso deal and schedule a follow-up task" }],
  tools,
});

// Execute the tool call with the user's vaulted Pipeline CRM access token
await sk.tools.executeTool(res.choices[0].message.tool_calls[0], "user_123");
import Anthropic from "@anthropic-ai/sdk";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);
const anthropic = new Anthropic();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["pipelinecrm"] }, pageSize: 100,
});

const msg = await anthropic.messages.create({
  model: "claude-sonnet-5",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Log a call note on the Contoso deal and schedule a follow-up task" }],
  tools,
});

// Tool call runs with the user's vaulted Pipeline CRM access token
await sk.tools.executeTool(msg.content, "user_123");
import { Agent } from "@google/adk/agents";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["pipelinecrm"] }, pageSize: 100,
});

const agent = new Agent({
  name: "sales_agent",
  model: "gemini-2.5-pro",
  instruction: "Pipeline CRM tools scoped to this user",
  tools,
});

await agent.run("Log a call note on the Contoso deal and schedule a follow-up task");
Try these prompts
Copy any prompt into your agent. Each maps directly to a Pipeline CRM tool. Click to copy, paste into your agent, done.
Deals
Copy the prompt
Copied
How much is in each pipeline stage right now?
Copy the prompt
Copied
Create a $24,000 deal for Contoso in the Qualified stage.
Copy the prompt
Copied
List deals owned by Sam.
People and activity
Copy the prompt
Copied
Find people at northwind.io.
Copy the prompt
Copied
Log a note on the Contoso deal summarizing today's call.
Copy the prompt
Copied
Create a follow-up task for the Contoso deal next Tuesday.
Projects and searches
Copy the prompt
Copied
Create an onboarding project from the Contoso deal.
Copy the prompt
Copied
List the milestones on the Contoso onboarding project.
Copy the prompt
Copied
Run my saved search called Hot leads.
SEE HOW AUTH WORKS
Each user connects their own Pipeline CRM access token once, and Scalekit sends it with every call. Tokens stay vaulted, every call is scope checked, and every action is logged.
1
Authorize
Your user connects
Pipeline CRM
once. We tie it to their identity and the meetings they approved — no shared bot account, no org-wide access
Who:
user ‘A’
when:
Once per user
access:
Limited to user
2
Store
Their
Pipeline CRM
token lives in a vault scoped to them. User A's meetings are never reachable by an agent acting for user B, even on the same connection
vault:
encrypted
scope:
per-user
tokens:
auto-refreshed
3
Resolve
When your agent calls a
Pipeline CRM
tool, we fetch the right token server-side. It never touches your agent, never appears in the LLM context, never shows up in your logs
speed:
~40ms
check:
before every call
seen by:
nobody
4
Audit
Every
Pipeline CRM
tool call is logged — who triggered it, which meeting was fetched, what came back. 90 days of history, tied to the user who authorized it
history:
90 days
export:
SIEM-ready
logged:
every call
Test other agents
See the same per-user auth pattern across other CRM and sales connectors.
GTM and RevOps Teams
CRM AI agent
Reads the Granola transcript after every call, extracts next steps and updates the HubSpot record, drafts the follow-up in Gmail, and confirms in Slack, all on the rep's own delegated OAuth.
GTM and RevOps Teams
Revenue forecast commentary
Pulls open pipeline from Salesforce and HubSpot, calculates coverage against quota, flags at-risk stages, posts commentary to Slack, and logs every snapshot to Google Sheets.
GTM and RevOps Teams
Deal intelligence agent
Pulls recent Gong calls, scores deal risk with an LLM, cross-references the record in Attio, and DMs each owner their at-risk deals in Slack. Every read is scoped to that rep's own access.
Test other agents
See the same per-user auth pattern across other CRM and sales connectors.
GTM
CRM AI agent
Turn each Granola call transcript into a HubSpot record update, a drafted Gmail follow-up, and a Slack recap.
GTM
Revenue forecast agent
Score pipeline coverage against quota across Salesforce and HubSpot, post forecast commentary to Slack, log snapshots to Sheets.
SALES
Deal intelligence agent
Score Gong call risk with an LLM, cross-reference the Attio record, and DM each owner their at-risk deals in Slack.
Why Scalekit
Secure your agent's access. Connectors ship in minutes
01.
Shared tokens break per-user analytics
A shared Pipeline CRM access token looks fine in a demo. In production every deal change and note looks like one service account, and you cannot tell which user triggered it. Scalekit resolves the credential of the actual user who triggered the agent, never a shared bot.
// shared token
audit → bot_service_account

// scalekit
audit → user_abc ✓
02.
Authentication is not authorization
03.
Multi-tenancy is architectural
04.
Pipeline CRM today. Ten connectors tomorrow.
“Our agents act across Salesforce, Gong, Google Drive, and more, on behalf of every customer. Scalekit behind the scenes meant we can keep adding tools without ever rebuilding how credentials or tool calling work.”
Venu Madhav Kattagoni
Head of Engineering / Von
FAQs
Frequently Asked Questions
Does the agent access Pipeline CRM as the user or through a shared access token?
As the user. Each user connects their own Pipeline CRM access token once, and Scalekit sends it with every call. Audit logs attribute every deal change, note, and task to that user, not a shared service account.
Where is the Pipeline CRM access token stored?
In Scalekit's managed AES-256 token vault, namespaced per tenant. To rotate it, the user reconnects with a new access token. Revocation is a single dashboard action. Credentials never appear in prompts, logs, or LLM context.
Can I limit what the agent does in Pipeline CRM?
Yes. Filter by tool name in listScopedTools to expose only what you want, for example deal and people tools without pipelinecrm_deal_delete or pipelinecrm_person_delete, which permanently delete records. Scalekit also enforces scope checks before every API call.
What happens when a user revokes Pipeline CRM access?
The connection is invalidated on the next tool call. Subsequent requests for that user fail closed with a clear error. Other users in the tenant remain unaffected. The event is logged for audit.
Can the agent report on the Pipeline CRM pipeline?
Yes. pipelinecrm_deal_totals_by_stage_get returns the count and total value of the deals the user can see in every stage, and pipelinecrm_deals_list returns the individual deals with filters for stage, pipeline, and owner.
Start in your coding agent
Up and running in one command
Install the Scalekit skill in your editor of choice. Connector, auth, tools, prompt, all wired up
Claude Code REPL
/plugin marketplace add scalekit-inc/claude-code-authstack
/plugin install agentkit@scalekit-auth-stack
Cursor Code REPL
# ~/.cursor/mcp.json
{
""mcpServers"": {
""pipelinecrm"": {
""url"": ""https://mcp.scalekit.com/pipelinecrm"",
""headers"": { ""Authorization"": ""Bearer $SCALEKIT_TOKEN"" }
}
}
}
Codex Code REPL
# ~/.codex/config.toml
[mcp_servers.pipelinecrm]
url = ""https://mcp.scalekit.com/pipelinecrm""
auth_env = ""SCALEKIT_TOKEN""
Copilot Code REPL
# .vscode/mcp.json
{
""servers"": {
""pipelinecrm"": {
""url"": ""https://mcp.scalekit.com/pipelinecrm"",
""type"": ""http""
}
}
}