LACRM MCP Server
LACRM MCP Server provides 88 tools for comprehensive Less Annoying CRM API access, covering records, workflows, bulk operations, and account settings.
Discover schemas, pipelines, users, calendars, groups, and custom fields before operations.
Create, edit, delete, retrieve, and search contacts/companies and pipeline items.
Manage tasks, events, notes, emails, files, relationships, and group memberships.
Configure custom fields, groups, pipelines, pipeline statuses, teams, and webhooks.
Run bulk CSV create/update workflows with template generation, dry-run validation, detached execution, status polling, and resume.
Use name-based resolution for statuses, users, calendars, and custom fields to avoid manual ID lookups.
Get accurate counts with
count_onlyauto-pagination and summary envelopes with breakdowns.Use flat-string shortcuts for contact email/phone/website and strict search input validation.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@LACRM MCP Server show my recent deals in pipeline"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
LACRM MCP Server
A Model Context Protocol (MCP) server for Less Annoying CRM that provides comprehensive API access through 88 tools.
Published as lacrm-mcp on npm (see the npm page or package.json for the current version).
Key Features
88 tools covering contacts, pipelines, tasks, events, notes, emails, files, relationships, groups, bulk CSV, and settings
Name resolution: Search tools accept human-readable names (status names, user names, calendar names, custom field names) and auto-resolve to IDs at runtime — no prerequisite lookup calls needed
count_only mode: All search/list tools support
count_only: truewhich auto-paginates through all results and returns accurate totals with categorical breakdowns — no manual pagination requiredFlat-string shortcuts:
email_address,phone_number,website_urlon contact create/edit auto-convert to the required array formatResponse summaries: List-returning tools wrap results in
{summary, results}envelopes with machine-counted page counts and breakdownsID sanitization: Defense-in-depth stripping of accidental quote characters from ID parameters
Resumable bulk runs: A long bulk import runs in a detached worker; if that process is interrupted, the run reports itself as
interruptedrather than hanging onrunning, and can be resumed at the first unprocessed row without reapplying completed rowsRate limiting: Client-side enforcement of 120 requests/minute with automatic waiting
Related MCP server: pipedrive-mcp
Installation
From npm (recommended for production)
npm install -g lacrm-mcpFrom source
git clone https://github.com/optimize-overseas/lacrm-mcp.git
cd lacrm-mcp
npm install
npm run buildConfiguration
Environment Variable (Recommended)
Set the LACRM_API_KEY environment variable:
export LACRM_API_KEY=your-api-keyConfig File
Alternatively, create a config file at ~/.lacrm-config.json:
{
"apiKey": "your-api-key"
}Debug logging (optional)
Set DEBUG to emit [DEBUG] diagnostics to stderr. For privacy, the per-call
debug line logs only the names of the parameters, never their values (CRM
parameters routinely contain PII such as contact names, addresses, and notes):
DEBUG=1 lacrm-mcpTo also log full parameter values for deep debugging, additionally set
LACRM_DEBUG_PARAMS=1. Even then, values that look like credentials (API keys,
tokens, bearer/authorization headers, private keys) are masked before logging.
Leave this unset in normal operation.
DEBUG=1 LACRM_DEBUG_PARAMS=1 lacrm-mcpThe API key itself is sent in the Authorization header and is never included
in the logged parameters.
Automatic retries (optional)
Read operations (all Get* API functions) are automatically retried on
transient failures - HTTP 429/500/502/503/504/522/524, network drops, and
request timeouts - using jittered exponential backoff that honors the
Retry-After header. Write operations (Create*/Edit*/Delete*) are never
retried, so a timed-out write cannot be duplicated. The total retry budget is
bounded so a call never runs past the single-request timeout ceiling.
Defaults are sensible; override them with environment variables if needed:
export LACRM_MAX_RETRIES=3 # retries after the first attempt
export LACRM_RETRY_BASE_MS=400 # backoff base (ms); doubles each attempt
export LACRM_RETRY_DEADLINE_MS=175000 # total wall-clock budget across attempts (ms)Claude Desktop Configuration
Add to your Claude Desktop configuration file (~/Library/Application Support/Claude/claude_desktop_config.json on macOS):
{
"mcpServers": {
"lacrm": {
"command": "node",
"args": ["/path/to/lacrm-mcp/build/index.js"],
"env": {
"LACRM_API_KEY": "your-api-key"
}
}
}
}Testing with MCP Inspector
npm run inspectorMCP Resources
This server provides workflow resources that help AI clients understand how to use the MCP effectively. Resources are discoverable via the standard MCP resources/list protocol.
Resource URI | Description |
| Start here - explains what tools to call before any operation |
| Detailed workflow for creating and editing contacts/companies |
| Detailed workflow for creating and editing pipeline items |
Usage: Call resources/list to discover available resources, then resources/read with the URI to get the content.
Response Format
Summary Envelopes
All list-returning tools wrap their results in a structured {summary, results} envelope. The summary provides machine-counted page counts and categorical breakdowns, which prevents LLMs from miscounting items in large JSON arrays -- a known failure mode when datasets exceed approximately 50 items.
Envelope structure:
{
"summary": {
"page_count": 15,
"has_more_results": false,
"by_status": {
"Active": 10,
"Closed - Won": 3,
"Closed - Lost": 2
}
},
"results": [
{ "...full pipeline item data..." },
{ "...full pipeline item data..." }
]
}The summary object always includes:
page_count-- the number of items on this page only (not the total across all pages)has_more_results-- whether more matching items exist beyond this page (v1.9.4: every list tool,search_contactsincluded). LACRM's ownHasMoreResultsflag decides whenever its answer carries one. When an answer has no flag (a bare array), a full page readstrue, because nothing says the list ended; only a short page readsfalse. A full page is as many items as the tool asked LACRM for, capped at LACRM's 10,000 per page: the tool'smax_results, whose default is 25 forsearch_contactsand LACRM's own 500 for the other list tools.get_files_attached_to_contactandget_pipeline_items_attached_to_contactread LACRM functions that are not paginated (they answer with every item at once), so theirhas_more_resultsisfalseunless LACRM itself says more.note(whenhas_more_resultsis true) -- a reminder thatpage_countis partial andcount_only=trueshould be used for accurate totals
Important: When has_more_results is true, the page_count value is NOT the total number of matching results. Use count_only=true for accurate totals across all pages.
Depending on the tool, the summary may also include one or more categorical breakdowns that group items by a relevant field.
Tools with Summary Envelopes
Tool | Breakdowns | Description |
|
| Counts by assigned user |
|
| Counts by pipeline status name |
|
| Counts by pipeline name and status name |
|
| Counts by completion (Yes/No) |
|
| Counts by completion (Yes/No) |
|
| Counts by send direction (Yes/No for UserIsSender) |
|
| Counts by send direction (Yes/No for UserIsSender) |
| (total only) | Page count and pagination status |
| (total only) | Page count and pagination status |
| (total only) | Page count and pagination status |
| (total only) | Page count and pagination status |
| (total only) | Page count and pagination status |
|
| Counts by assigned user |
Single-record tools (e.g., get_contact, get_task, get_pipeline_item) return the raw API response directly without a summary envelope.
Name Resolution (v1.3.0)
Many LACRM API parameters require internal IDs (status IDs, user IDs, calendar IDs, custom field IDs). In v1.3.0, name-based alternatives were added so the caller can pass human-readable names instead. The server resolves names to the values the LACRM API expects at runtime — status/user/calendar IDs, and (for custom fields) the field name LACRM writes by. All lookups are case-insensitive, and if a name cannot be resolved the error message lists all available options.
These parameters are instance-agnostic -- they work with any LACRM account regardless of how statuses, users, calendars, or custom fields are configured.
Name Resolution Parameters
Parameter | Available On | Replaces (mutually exclusive) |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
How It Works
The caller passes a name-based parameter (e.g.,
status_name: "Active")The server queries the relevant API endpoint (e.g.,
GetPipelineStatuses)A case-insensitive match resolves the name to its ID
The resolved ID is used for the actual API call
If no match is found, an error lists all available names
For user_name_filter, matching works against full name ("First Last"), first name only, or last name only.
For custom_field_names, dropdown fields are additionally validated -- if the supplied value is not among the allowed options, an error lists the valid choices.
Example
Instead of:
{
"pipeline_id": "abc123",
"status_id": "def456",
"custom_fields": { "cf_789": "Referral" }
}Use:
{
"pipeline_id": "abc123",
"status_name": "Active",
"custom_field_names": { "Lead Source": "Referral" }
}Count Mode (v1.3.0)
All search and list tools support a count_only parameter. When set to true, the tool auto-paginates through all pages (up to a safety cap of 100 pages) and returns only aggregate counts with breakdowns -- no results array is included. This is useful for questions like "how many deals are in each status?" without transferring the full dataset.
Supported Tools
Tool | Breakdowns in Count Mode |
|
|
|
|
|
|
|
|
|
|
| (total only) |
| (total only) |
| (total only) |
| (total only) |
|
|
|
|
|
|
Count Mode Response
{
"total": 47,
"complete": true,
"breakdowns": {
"by_status": {
"Active": 30,
"Closed - Won": 12,
"Closed - Lost": 5
}
}
}When count_only is true:
The tool paginates through all available pages automatically
No
resultsarray is returned -- onlytotal,completeandbreakdownsA safety cap of 100 pages prevents runaway pagination
complete(v1.9.4) istrueonly when the walk reached the last page. When the cap (or an empty page the API still says has more behind it) stops it first,completeisfalse,totalis a lower bound, and anotesays so.
Strict Search Input (v2.0.0)
Breaking in v2.0.0. Calls that 1.x accepted are now refused: any unknown argument to a search tool, and a search_contacts call with no filter (pass allow_unfiltered: true to keep the old behaviour).
search_contacts, search_pipeline_items, search_notes, search_tasks, search_events and search_emails accept only the arguments their schemas list, and refuse anything else instead of ignoring it.
Before v2.0.0 the MCP SDK silently dropped an unknown argument, so a call such as {"name": "Smith"} ran as a search with no filter at all: a read of every record in the account, which is slow and can time out on a large account (with count_only, a walk of every page).
Unknown arguments are refused by all six tools, at the top level and (for
search_contactsandsearch_pipeline_items) inside anadvanced_filtersitem. The error names each unknown key;search_contactsalso lists the accepted ones. The advertised input schemas sayadditionalProperties: false.search_contactsonly: a filter is required: at least one of a non-blanksearch_terms, a non-emptyadvanced_filters, or anowner_filterwith a non-blank user ID. A search with none is refused before any API call.search_contactsonly:allow_unfiltered: trueis the explicit opt-in for a search with no filter, when every record really is what you want. It is not sent to the API.
For a person's name, advanced_filters on LastName / FirstName / FullName with Contains matches the name fields only; search_terms matches the text anywhere in a record.
{"advanced_filters": [{"Name": "LastName", "Operation": "Contains", "Value": "Smith"}]}Flat-String Shortcuts (v1.3.0)
create_contact and edit_contact accept simplified string parameters for common single-value fields:
Shortcut Parameter | Expands To | Type |
|
| Work email |
|
| Work phone |
|
| Website |
Each shortcut is mutually exclusive with its corresponding array parameter (e.g., email_address cannot be used together with email). This eliminates the need to construct array-of-objects structures for the common case of a single value.
Example
Instead of:
{
"name": "Jane Doe",
"email": [{"Text": "jane@example.com", "Type": "Work"}],
"phone": [{"Text": "555-0100", "Type": "Work"}]
}Use:
{
"name": "Jane Doe",
"email_address": "jane@example.com",
"phone_number": "555-0100"
}Bulk CSV Operations (v1.4.0)
Import or update contacts in bulk from a CSV, paced to LACRM's 1-request/second guidance. Five tools cover the workflow, and everything is instance-agnostic: the caller supplies the entire field configuration (which CSV columns map to which LACRM fields, how each one merges, and any create-time defaults) as tool arguments. No field names, merge rules, or use cases are built into the server.
Tool | Purpose |
| Produce a ready-to-fill CSV header plus a per-field report explaining what populating / blanking / omitting each column does |
| Dry-run validation (no writes): row count, present vs. preserved columns, missing required columns/values, duplicate keys, and a time estimate |
| Launch a detached, throttled worker; returns a |
| Progress, per-row errors, and the path to the final report CSV |
| Continue a run whose worker stopped before finishing, from the first unprocessed row |
Template column order: generated templates list LACRM built-in fields first — the key column, then the contact name, then the address block, then any other standard fields (Email, Phone, etc.) — and custom fields last. Columns read left-to-right as identity → standard → custom, regardless of the order fields are supplied in.
Update merge model (column-presence)
Bulk updates are read-merge-write per contact, so a partial CSV never clobbers fields it does not mention. A column absent from the CSV is always left unchanged. When a column is present, its strategy decides what happens:
Strategy | Cell has a value | Cell is blank | Column absent |
| overwrites the field | clears the field | preserved |
| overwrites the field | preserved (ignored) | preserved |
| added to the existing semicolon-delimited list (de-duplicated) | preserved | preserved |
| always preserved | always preserved | preserved |
Use replace for fields that should mirror the CSV exactly (a blank cell means "clear it"); preserve_if_blank for fill-only fields; union_semicolon for accumulate-style list fields; never_write to lock a field against this operation.
Update address columns (append-if-absent, v1.5.0)
Update mode can also carry a structured address via address_config (same shape as create's address: street1, optional street2/city/state/zip/country, and a literal type defaulting to Work). Its mapped CSV columns are added to the generated template and recognized by validation. For each row the uploaded address is appended to the contact only if it is not already on the record — compared case- and format-insensitively on Street/City/State/Zip, with street-suffix and directional abbreviations canonicalized (St↔Street, N↔North), a US ZIP+4 reduced to its 5-digit base (international postal codes are kept whole, so two codes that differ only past the 5th character stay distinct), and a full state name matched to its 2-letter code. On a match the existing CRM address is kept and the file's value is ignored; existing addresses are never modified, reordered, or removed — the new one is appended at the end (the primary/mailing address at position 0 is untouched). Because LACRM's EditContact replaces the entire address array, the worker reads the contact's existing addresses and writes back the complete merged array. One address per row.
Throttle & detached execution
bulk_execute spawns a separate worker process that calls LACRM strictly sequentially at >=1s spacing, so a multi-thousand-row run (which can take hours) proceeds independently of the request that started it. Run state is persisted to disk — directory configurable via LACRM_BULK_RUNS_DIR (default: a lacrm-bulk-runs folder under the OS temp dir).
Interrupted runs & resume (v1.8.0)
If a run is interrupted, resume it — don't start over. The worker is an ordinary process: restarting the host, or killing it, ends the run. What survives is its state, which is rewritten after every row.
Reported | Meaning |
| a worker is alive and recording progress |
| the run stopped without finishing — resumable |
| every row processed; |
| the worker hit a fatal error and recorded it in |
bulk_run_statusreports an interrupted run asstatus: "interrupted"— withstored_status,interrupted_reason,resumable, andseconds_since_progress— instead of reportingrunningforever. Interruption is detected from the worker's recorded process id and from how long the run has been silent, so neither a dead worker nor a process id later recycled onto an unrelated process is mistaken for progress. The check is derived when you read it and never rewrites state, so it cannot race a live worker.bulk_run_resumerelaunches the worker for that run. Processing continues at the first unprocessed row; rows already applied are never applied again. It refuses if the run has finished, if nothing is left to process, or if the run is still actively being worked on — resuming a live run would process rows twice.
The silence threshold is deliberately generous (at least 15 minutes, scaled up for slower pacing): a single row can legitimately take a while when the API is slow and the client is retrying, and wrongly declaring a healthy run dead is worse than noticing a stopped one late.
Typical workflow
bulk_generate_template-> hand the user the CSV to fill and the per-field behavior report.bulk_validate_csv-> review row counts, which fields will change vs. be preserved, and any blocking errors. Always preview before executing.bulk_executewithconfirm: true-> receive arun_id.bulk_run_status-> poll untilstatusiscompleted, then fetch the report CSV. If it reportsinterrupted, callbulk_run_resumewith the samerun_idand keep polling.
Available Tools
Discovery Tools (10)
Tool | Description |
| START HERE - Get the workflow guide explaining what tools to call before any operation |
| Get complete field schema for contacts (fixed + custom fields) |
| Get complete field schema for companies (fixed + custom fields) |
| Get complete field schema for pipeline items (fixed + custom fields) |
| Get custom field definitions with optional filtering by record type and pipeline |
| Get custom fields for a specific pipeline with required/optional status |
| Get all pipelines with their statuses |
| Get all groups in the account |
| Get all users in the account |
| Get all calendars in the account |
Contact Tools (6)
Tool | Description |
| Create a new contact or company |
| Update an existing contact |
| Delete a contact |
| Get a contact by ID |
| Get multiple contacts by IDs (up to 200) |
| Search contacts by name, email, phone, or custom fields. Needs a filter, and refuses unknown arguments (v2.0.0 - see Strict search input) |
Bulk CSV Tools (5)
See Bulk CSV Operations for the full workflow and merge model.
Tool | Description |
| Generate a ready-to-fill CSV template + per-field behavior report for a bulk operation |
| Dry-run validation of a bulk CSV against a field configuration (no writes) |
| Launch a detached, throttled (1 req/sec) bulk create/update worker; returns a run id |
| Get progress, per-row errors, and the report CSV for a bulk run |
| Resume an interrupted bulk run at the first unprocessed row |
Event Tools (6)
Tool | Description |
| Create a calendar event |
| Update an existing event |
| Delete an event |
| Get an event by ID |
| Search events with filters |
| Get all events for a contact |
Task Tools (6)
Tool | Description |
| Create a task |
| Update an existing task |
| Delete a task |
| Get a task by ID |
| Search tasks with filters |
| Get all tasks for a contact |
Note Tools (6)
Tool | Description |
| Create a note for a contact |
| Update an existing note |
| Delete a note |
| Get a note by ID |
| Search notes with filters |
| Get all notes for a contact |
Pipeline Item Tools (7)
Tool | Description |
| Create a pipeline item (deal/opportunity) |
| Update a pipeline item |
| Delete a pipeline item |
| Delete multiple pipeline items |
| Get a pipeline item by ID |
| Search pipeline items with filters |
| Get all pipeline items for a contact |
Email Tools (5)
Tool | Description |
| Log an email in the CRM |
| Get a logged email by ID |
| Search logged emails with filters |
| Get all emails for a contact |
| Delete a logged email |
File Tools (3)
Tool | Description |
| Upload a file and attach to a contact |
| Get file info and download URL |
| Get all files for a contact |
Relationship Tools (5)
Tool | Description |
| Create a relationship between contacts |
| Update a relationship |
| Delete a relationship |
| Get a relationship by ID |
| Get all relationships for a contact |
Group Membership Tools (4)
Tool | Description |
| Add a contact to a group |
| Remove a contact from a group |
| Get all groups a contact belongs to |
| Get all contacts in a group |
Custom Field Settings Tools (4)
Tool | Description |
| Create a new custom field definition |
| Update an existing custom field |
| Delete a custom field |
| Get details for a single custom field |
Group Settings Tools (4)
Tool | Description |
| Create a new group |
| Update a group's properties |
| Delete a group |
| Get details for a single group |
Pipeline Settings Tools (4)
Tool | Description |
| Create a new pipeline |
| Update a pipeline's configuration |
| Delete a pipeline |
| Get details for a single pipeline |
Pipeline Status Settings Tools (4)
Tool | Description |
| Create a new status for a pipeline |
| Update a pipeline status |
| Delete a pipeline status |
| Get all statuses for a pipeline |
Team Settings Tools (5)
Tool | Description |
| Create a new team |
| Update a team's name or membership |
| Delete a team |
| Get details for a single team |
| Get all teams |
Webhook Settings Tools (4)
Tool | Description |
| Create a new webhook |
| Get details for a single webhook |
| Get all webhooks |
| Delete a webhook |
Custom Fields
Using custom_field_names (Recommended -- v1.3.0)
Pass field names directly as keys. The server resolves names to IDs automatically and validates dropdown values:
{
"custom_field_names": {
"Lead Source": "Referral",
"Deal Value": 50000,
"Expected Close": "2025-03-15"
}
}Invalid field names return an error listing available fields. Invalid dropdown values return an error listing valid options.
Using custom_fields (verbatim, by field name — no validation)
LACRM v2 writes custom fields by their name at the top level; a numeric CustomFieldId is silently ignored on write.
custom_fieldswrites its keys verbatim, so use field names as keys. Usecustom_field_namesinstead when you want dropdown/option validation.
Call
get_custom_fieldswithrecord_type="Contact"orrecord_type="Company"(for contacts/companies) orget_pipeline_custom_fieldswith thepipeline_id(for pipeline items)Note the field names, types, required status, and valid options
Use field names as keys in the
custom_fieldsparameter
Example:
{
"custom_fields": {
"Lead Source": "Referral",
"Deal Value": 50000,
"Expected Close": "2025-03-15"
}
}Pipeline Support
Workflow for creating pipeline items:
Call
get_pipelinesto discover pipeline IDsUse
create_pipeline_itemwithpipeline_idand eitherstatus_name(auto-resolves, v1.3.0) orstatus_idOptionally include
custom_field_names(v1.3.0) orcustom_fieldsfor pipeline custom fields
The tools provide clear error messages when required fields are missing or names don't match.
API Reference
This MCP server wraps the Less Annoying CRM API v2. All API calls are made to https://api.lessannoyingcrm.com/v2/.
Rate Limiting
The MCP server enforces rate limiting to protect LACRM's API:
Limit: 120 requests per minute (sliding window)
Behavior: If the limit is reached, requests automatically wait until a slot is available
No configuration needed: Rate limiting is always active
This ensures that even aggressive AI usage won't overwhelm LACRM's servers.
Security
Authentication
API key is loaded from
LACRM_API_KEYenvironment variable (recommended)Fallback to config file at
~/.lacrm-config.jsonAPI key is never logged or exposed in error messages
ID Parameter Sanitization
The server includes defense-in-depth sanitization for all ID parameters. LLMs sometimes over-quote values, passing "\"12345\"" (a string with embedded literal quotes) instead of the clean string "12345". The LACRM API rejects values with embedded quotes as invalid UIDs.
To guard against this, the client automatically strips surrounding single and double quote characters from any parameter whose key ends with:
*Id-- single ID parameters (e.g.,ContactId,PipelineId)*Ids-- array-of-ID parameters (e.g.,ContactIds)*IdList-- ID list parameters
When sanitization occurs, a warning is logged so the issue can be traced. Other string parameters (names, notes, descriptions, etc.) are never modified.
File Upload Security
The create_file tool validates file paths to prevent:
Path traversal attacks (
../sequences)Access to sensitive directories (
.git,.env,.ssh,.aws,node_modules, etc.)
Input Validation
All tool inputs are validated with Zod schemas
Error responses use
isError: trueflag for LLM-friendly handlingNo shell command execution - all operations use direct API calls
License
MIT
Available Tools
88 toolsadd_contact_to_groupAdd Contact to GroupA
Add a contact to a group in Less Annoying CRM. Use either group_id or group_name to identify the group (not both).
Use get_groups to find valid group IDs.
Inputs: contact_id (required), group_id, group_name.
bulk_executeBulk: Execute (live)A
Execute a bulk create/update by launching a detached background worker that paces calls at ~1 request/second (LACRM's agreement). Returns a run_id immediately.
SAFETY: this performs LIVE writes. It re-validates first and refuses to run if validation fails. You must pass confirm=true to proceed (omitting it returns the validation only). Always show the user a bulk_validate_csv preview and obtain explicit approval before passing confirm=true.
ASYNC COMPLETION (optional): pass channel + requestor_email + identifier (and request_summary) and the finished result - including the report delivered as an editable Google Sheet - is posted back on the originating channel automatically when the run completes; no polling needed. Without them, poll bulk_run_status as before.
Update mode uses per-field merge strategies (see fields[].strategy); an absent column is left unchanged. Provide the CSV as csv_content or csv_path.
Inputs: operation (required), fields, channel, confirm, +10 more.
bulk_generate_templateBulk: Generate CSV TemplateA
Generate a ready-to-fill CSV template for a bulk operation, plus a per-field report describing exactly what happens when each column is populated, left blank, or omitted.
The template is generated from the SAME field configuration the validate/execute tools use, so it always reflects the rules that will actually be applied. Supply the field configuration as arguments; nothing about any specific CRM is built in.
Returns: { csv, columns, report } where report[].behavior explains each field's merge strategy. Columns are ordered LACRM built-in fields first (key, owner name, address block, then other standard fields), then custom fields.
Inputs: fields (required), operation (required), key_column, address_config, +2 more.
bulk_run_resumeBulk: Resume RunA
Continue a bulk run whose worker stopped before finishing (host restart, killed process). Progress is persisted after every row, so the run resumes at the first unprocessed row and rows that were already applied are never applied again. Refuses if the run is already finished or still actively running.
Inputs: run_id (required).
bulk_run_statusBulk: Run StatusA
Get the status of a bulk run started by bulk_execute. Returns progress (processed/total), success/failure counts, per-row errors, and the path to the final report CSV when complete.
Inputs: run_id (required).
bulk_validate_csvBulk: Validate CSV (dry run)A
Validate a bulk CSV against a field configuration WITHOUT making any changes.
Reports row count, which configured columns are present (will be acted on) vs absent (left unchanged), unknown columns, missing required columns/values, duplicate keys, and a rough time estimate (runs are paced at ~1 request/second). Always run this and review it before bulk_execute.
Provide the CSV as csv_content (inline) or csv_path (a readable file path).
Inputs: fields (required), operation (required), csv_path, key_column, +3 more.
create_contactCreate ContactA
Create a new contact or company in Less Annoying CRM.
PREREQUISITES (call these first):
get_contact_schema (or get_company_schema for companies) → see ALL fields (required and optional), their types, and formats
get_users → get valid user IDs for the required assigned_to field
Use this tool when you need to add a new person or company to the CRM. Set is_company to true to create a company record instead of a person.
Supports flat-string shortcuts: use email_address, phone_number, or website_url for single values instead of the array format. Supports custom_field_names for name-based custom field resolution.
Returns the new ContactId on success.
Inputs: name (required), is_company (required), assigned_to (required), email, +13 more.
create_custom_fieldCreate Custom FieldA
Create a new custom field definition in Less Annoying CRM. Use this to add new fields for contacts, companies, or pipelines.
Field types: Currency, Date, Dropdown, RadioList, Checkbox, Number, Text, TextArea, ContactLink, FileLink, Signature, Section, SectionHeader, TextBlock.
For Dropdown/RadioList/Checkbox fields, provide options array. For Pipeline fields, pipeline_id is required.
Inputs: name (required), type (required), options, is_required, +5 more.
create_emailCreate EmailA
Log an email in Less Annoying CRM. Use this to record email correspondence with contacts for tracking purposes.
Required: contact_ids, from, to, body, date. The email is attached to the specified contacts' history.
Inputs: to (required), body (required), date (required), from (required), +4 more.
create_eventCreate EventA
Create a calendar event in Less Annoying CRM. Use this tool to schedule meetings, calls, or other time-specific activities. Events can be attached to contacts and assigned to specific calendars.
Required: name, start_date, end_date. Use get_calendars to find valid calendar IDs. Use get_users to find valid user IDs for attendees.
Supports recurring events with RFC 5545 recurrence rules (e.g., "FREQ=WEEKLY;BYDAY=MO,WE,FR").
Inputs: name (required), end_date (required), start_date (required), location, +7 more.
create_fileCreate FileA
Upload a file and attach it to a contact in Less Annoying CRM. Supports two input methods:
file_base64: Base64-encoded file content (for smaller files)
file_path: Local file path (server reads and uploads)
Required: contact_id, and either file_base64 or file_path. Maximum file size: 50MB.
Inputs: contact_id (required), file_name, file_path, mime_type, +1 more.
create_groupCreate GroupA
Create a new group in Less Annoying CRM. Groups are used to segment contacts for easy retrieval.
Sharing options:
Public: Visible to all users
Private: Only visible to creator
Teams: Visible to specified teams (requires team_ids)
Inputs: name (required), color, sharing, team_ids.
create_noteCreate NoteA
Create a new note attached to a contact in Less Annoying CRM. Notes are timestamped text entries that appear in contact history.
Required: contact_id, note. The note text preserves newlines but escapes HTML/markdown.
Inputs: note (required), contact_id (required), date_displayed.
create_pipelineCreate PipelineA
Create a new pipeline in Less Annoying CRM. Pipelines track deals, opportunities, or any workflow with stages.
Permissions:
Public: Visible to all users
TeamSharing: Only visible to specified teams (requires team_ids)
Inputs: icon (required), name (required), team_ids, permissions.
create_pipeline_itemCreate Pipeline ItemA
Create a new pipeline item attached to a contact in Less Annoying CRM.
PREREQUISITES (call these first):
get_pipelines → find pipeline_id and valid status_ids
get_pipeline_item_schema(pipeline_id) → see required custom fields and their valid options
search_contacts → find/verify valid contact_id
Pipeline items track contacts through sales stages or workflows. Optionally run status automation when creating (e.g., send emails, create tasks).
Supports name-based resolution: use status_name instead of status_id, and custom_field_names instead of custom_fields.
Inputs: contact_id (required), pipeline_id (required), note, status_id, +4 more.
create_pipeline_statusCreate Pipeline StatusA
Create a new status for an existing pipeline. Statuses represent stages in your pipeline workflow.
is_active:
true: Status represents an active/in-progress stage
false: Status represents a closed/completed stage
Colors: Blue, LightBlue, Cyan, Teal, Green, LimeGreen, Yellow, Orange, Red, Pink, Magenta, Purple, Indigo, Gray, or hex codes like #486581
Inputs: name (required), pipeline_id (required), color, is_active.
create_relationshipCreate RelationshipA
Create a relationship between two contacts or companies. Relationships are bi-directional and visible on both contact records. Use the note field to describe the relationship type (e.g., "Spouse", "Referred by").
Inputs: note (required), contact_id_1 (required), contact_id_2 (required).
create_taskCreate TaskA
Create a new task in Less Annoying CRM. Tasks are reminders that appear on user task lists and daily agenda emails. Unlike events, tasks are date-only (no time component).
Required: name. Optional: due_date, assigned_to, contact_id for linking to a contact. Use get_users to find valid user IDs for assigned_to. Use get_calendars to find valid calendar IDs.
Inputs: name (required), due_date, contact_id, assigned_to, +2 more.
create_teamCreate TeamA
Create a new team in Less Annoying CRM. Teams organize users for permission management. Use get_users first to find user IDs for team membership.
Inputs: name (required), user_ids.
create_webhookCreate WebhookA
Create a new webhook in Less Annoying CRM. Webhooks send POST requests to your URL when events occur.
Requirements:
endpoint_url must be HTTPS
Your endpoint must respond to an initial handshake request
Scope:
User: Only triggers for actions by the authenticated user
Account: Triggers for actions by any user in the account
Common events: Contact.Create, Contact.Edit, Contact.Delete, PipelineItemStatus.Create, PipelineItemStatus.Edit
Inputs: events (required), endpoint_url (required), webhook_scope (required).
delete_contactDelete ContactA
Permanently delete a contact or company from Less Annoying CRM. WARNING: This action cannot be undone. The contact and all associated data will be removed.
Required: contact_id. Use search_contacts or get_contact to find valid contact IDs before deleting.
Inputs: contact_id (required).
delete_custom_fieldDelete Custom FieldA
Delete a custom field definition. WARNING: This permanently removes the field and all data stored in it across all records.
Inputs: custom_field_id (required), section_deletes_fields.
delete_emailDelete EmailA
Delete a logged email from a contact's profile. WARNING: This permanently removes the email record.
Inputs: email_id (required).
delete_eventDelete EventA
Delete a calendar event from Less Annoying CRM. WARNING: This permanently removes the event from all attendee calendars.
Required: event_id.
Inputs: event_id (required).
delete_groupDelete GroupA
Delete a group from the account. WARNING: This removes the group but does not delete the contacts in it.
Inputs: group_id (required).
delete_noteDelete NoteA
Delete a note from a contact's profile in Less Annoying CRM. WARNING: This permanently removes the note.
Required: note_id.
Inputs: note_id (required).
delete_pipelineDelete PipelineA
Delete a pipeline from the account. WARNING: This permanently removes the pipeline configuration. Pipeline items may become orphaned.
Inputs: pipeline_id (required).
delete_pipeline_itemDelete Pipeline ItemA
Delete a single pipeline item from Less Annoying CRM. WARNING: This permanently removes the item.
Required: pipeline_item_id.
Inputs: pipeline_item_id (required).
delete_pipeline_items_bulkDelete Pipeline Items (Bulk)A
Delete multiple pipeline items at once from Less Annoying CRM. All items must belong to the same pipeline. Maximum 5000 items per call.
Returns count of processed and skipped items.
Inputs: pipeline_id (required), pipeline_item_ids (required).
delete_pipeline_statusDelete Pipeline StatusB
Delete a pipeline status. WARNING: Pipeline items using this status may become orphaned.
Inputs: status_id (required).
delete_relationshipDelete RelationshipA
Delete a relationship between two contacts. WARNING: This permanently removes the relationship from both contact records.
Inputs: relationship_id (required).
delete_taskDelete TaskA
Permanently delete a task from Less Annoying CRM. WARNING: Consider using edit_task with is_complete=true instead to preserve history.
Required: task_id.
Inputs: task_id (required).
delete_teamDelete TeamA
Delete a team from the account. Only account owners and administrators can delete teams. WARNING: This removes the team but does not affect the users in it.
Inputs: team_id (required).
delete_webhookDelete WebhookA
Delete a webhook from the account. The webhook will stop sending events immediately.
Inputs: webhook_id (required).
edit_contactEdit ContactA
Update an existing contact or company in Less Annoying CRM.
PREREQUISITES (call these first):
get_contact_schema (or get_company_schema) → see available fields, their types, and formats
search_contacts or get_contact → find/verify valid contact_id
Use this tool to modify contact details like name, email, phone, etc. Only include fields you want to change - other fields remain unchanged.
Supports flat-string shortcuts: use email_address, phone_number, or website_url for single values. Supports custom_field_names for name-based custom field resolution.
Inputs: contact_id (required), name, email, phone, +14 more.
edit_custom_fieldEdit Custom FieldA
Update an existing custom field definition. Use get_custom_fields to find field IDs first.
Note: You cannot change the field type after creation.
Inputs: custom_field_id (required), name, options, is_required, +3 more.
edit_eventEdit EventA
Update an existing calendar event in Less Annoying CRM. Only include fields you want to change - other fields remain unchanged.
Required: event_id. Use search_events or get_event to find valid event IDs.
Inputs: event_id (required), name, end_date, location, +8 more.
edit_groupEdit GroupA
Update an existing group's properties. Use get_groups to find group IDs first.
Inputs: group_id (required), name, color, sharing, +1 more.
edit_noteEdit NoteA
Update an existing note in Less Annoying CRM. Only include fields you want to change.
Required: note_id. Note content is completely replaced when updated.
Inputs: note_id (required), note, date_displayed.
edit_pipelineEdit PipelineA
Update an existing pipeline's configuration. Use get_pipelines to find pipeline IDs first.
Inputs: pipeline_id (required), icon, name, team_ids, +1 more.
edit_pipeline_itemEdit Pipeline ItemA
Update an existing pipeline item in Less Annoying CRM.
PREREQUISITES (call these first):
get_pipeline_item_schema(pipeline_id) → see available custom fields and their valid options
search_pipeline_items or get_pipeline_item → find/verify valid pipeline_item_id
get_pipelines → find valid status_ids (if changing status)
Use this to change status, add notes, or update custom field values. Supports name-based resolution: use status_name instead of status_id, and custom_field_names instead of custom_fields.
Inputs: pipeline_item_id (required), note, status_id, pipeline_id, +4 more.
edit_pipeline_statusEdit Pipeline StatusA
Update an existing pipeline status. This modifies the status definition, not individual pipeline items. Only include fields you want to change. Use get_pipeline_statuses to find status IDs.
Inputs: status_id (required), name, color, is_active.
edit_relationshipEdit RelationshipA
Update the note on an existing relationship. The note describes the nature of the relationship between contacts.
Inputs: note (required), relationship_id (required).
edit_taskEdit TaskA
Update an existing task in Less Annoying CRM. Use this tool to modify task details or mark tasks as complete. Only include fields you want to change.
Required: task_id. Use is_complete=true to mark a task as done (preferred over deleting). Pass contact_id=null to detach from a contact.
Inputs: task_id (required), name, due_date, contact_id, +4 more.
edit_teamEdit TeamA
Update a team's name and/or membership. Use get_teams to find team IDs first.
Note: Passing user_ids completely replaces team membership. Pass empty array to remove all users.
Inputs: team_id (required), name, user_ids.
get_calendarsGet CalendarsA
Retrieve all calendars in this LACRM account. Use this tool to discover calendar IDs when creating events. Returns calendar IDs, names, and associated user IDs.
Each user typically has their own calendar. Use CalendarId when creating calendar events.
Inputs: no named parameters.
get_company_schemaGet Company SchemaA
Get complete field schema for creating/editing companies.
Returns ALL fields (both fixed system fields and custom fields) with:
name: The parameter name to use in create_contact (with is_company=true)
required: Whether this field must be provided
type: Field type (Text, Array, etc.)
input_format: Exact format expected for the value
is_custom_field: Whether this is a custom field (true) or built-in (false)
notes: Additional guidance for using this field
ALWAYS call this before creating a company to understand what data is needed. Note: Companies are created using create_contact with is_company=true.
Inputs: no named parameters.
get_contactGet ContactA
Retrieve a single contact or company by ID. Use this when you already have a ContactId and need the record.
NOTE: search_contacts returns the same full data for each match. Only use get_contact when you have an ID but not the data (e.g., from a webhook or external reference).
Inputs: contact_id (required).
get_contacts_by_idsGet Contacts By IDsA
Retrieve multiple contacts or companies by their IDs. Use this when you have a list of ContactIds (e.g., from webhooks or external references).
RETURNS FULL DATA: Each result includes all contact fields - same as search_contacts or get_contact. Maximum 10,000 results per call.
Inputs: contact_ids (required), page, max_results.
get_contact_schemaGet Contact SchemaA
Get complete field schema for creating/editing contacts.
Returns ALL fields (both fixed system fields and custom fields) with:
name: The parameter name to use in create_contact/edit_contact
required: Whether this field must be provided
type: Field type (Text, Array, Date, etc.)
input_format: Exact format expected for the value
is_custom_field: Whether this is a custom field (true) or built-in (false)
notes: Additional guidance for using this field
ALWAYS call this before creating a contact to understand what data is needed.
Inputs: no named parameters.
get_contacts_in_groupGet Contacts in GroupA
Retrieve all contacts that belong to a specific group. Use either group_id or group_name to identify the group (not both). Use count_only=true for accurate counts without returning the full result set.
Inputs: page, group_id, count_only, group_name, +1 more.
get_custom_fieldGet Custom FieldA
Get detailed information about a single custom field definition. Returns field name, type, options, display settings, and archived status.
Inputs: custom_field_id (required).
get_custom_fieldsGet Custom FieldsA
Retrieve custom field definitions for this LACRM account. Use this tool FIRST when you need to work with contacts or pipeline items that have custom fields.
IMPORTANT: Returns field details including:
name: The field name to use as key when setting values
required: Whether this field must be provided
type: The field type (Text, Number, Dropdown, etc.)
input_format: Description of expected value format
valid_options: For Dropdown/RadioList/Checkbox, the allowed values
Filter options:
record_type: "Contact", "Company", or "Pipeline" to filter by type
pipeline_id: Get fields for a specific pipeline (required when record_type is "Pipeline")
Example: To create a pipeline item, first call get_custom_fields with record_type="Pipeline" and the pipeline_id. Then use the field names as keys in custom_fields: { "FieldName": "value" }
Inputs: pipeline_id, record_type, include_archived.
get_emailGet EmailA
Retrieve a single logged email by ID. Use this when you already have an EmailId and need the record.
NOTE: search_emails returns the same full data for each match. Only use get_email when you have an ID but not the data.
Inputs: email_id (required).
get_emails_attached_to_contactGet Emails For ContactA
Retrieve all logged emails for a specific contact. RETURNS FULL DATA: Each result includes all email fields - no need to call get_email afterward. Use count_only=true for accurate counts without returning the full result set.
Inputs: contact_id (required), page, count_only, max_results.
get_eventGet EventA
Retrieve a single calendar event by ID. Use this when you already have an EventId and need the record.
NOTE: search_events returns the same full data for each match. Only use get_event when you have an ID but not the data.
Inputs: event_id (required).
get_events_attached_to_contactGet Events For ContactA
Retrieve all calendar events for a specific contact. RETURNS FULL DATA: Each result includes all event fields - no need to call get_event afterward. Use count_only=true for accurate counts without returning the full result set.
Inputs: contact_id (required), page, count_only, max_results.
get_fileGet FileA
Retrieve file information and a temporary download URL. NOTE: The download URL expires after 5 minutes. Call this again if you need a fresh URL.
Returns file metadata including name, size, type, and download link.
Inputs: file_id (required).
get_files_attached_to_contactGet Files For ContactA
Retrieve all files attached to a specific contact. Optionally include previous file versions. NOTE: Does not include files attached via File Link custom fields.
Inputs: contact_id (required), include_versions.
get_groupGet GroupA
Get details for a single group. Returns group name, sharing settings, team IDs, and color. Does not include contact membership data - use get_contacts_in_group for that.
Inputs: group_id (required).
get_groupsGet GroupsA
Retrieve all contact groups defined in this LACRM account. Use this tool to discover available groups before adding contacts to groups. Returns group IDs, names, and descriptions.
Groups are used to organize contacts (e.g., "VIP Customers", "Newsletter Subscribers"). Use the GroupId when managing group memberships.
Inputs: no named parameters.
get_groups_for_contactGet Groups For ContactB
Retrieve all groups a contact belongs to.
Inputs: contact_id (required), page, max_results.
get_noteGet NoteA
Retrieve a single note by ID. Use this when you already have a NoteId and need the record.
NOTE: search_notes returns the same full data for each match. Only use get_note when you have an ID but not the data.
Inputs: note_id (required).
get_notes_attached_to_contactGet Notes For ContactA
Retrieve all notes for a specific contact. RETURNS FULL DATA: Each result includes all note fields - no need to call get_note afterward. Use count_only=true for accurate counts without returning the full result set.
Inputs: contact_id (required), page, count_only, max_results.
get_pipelineGet PipelineA
Get detailed information about a single pipeline configuration. Returns pipeline name, icon, statuses, permissions, and sharing settings. Does not return pipeline items - use search_pipeline_items for that.
Inputs: pipeline_id (required).
get_pipeline_custom_fieldsGet Pipeline Custom FieldsA
Get custom fields for a specific pipeline - use this before creating or editing pipeline items.
Returns all custom fields configured for the pipeline with:
name: The field name to use as key in custom_fields parameter
required: Whether this field MUST be provided when creating pipeline items
type: Field type (Text, Number, Dropdown, etc.)
input_format: Description of the expected value format
valid_options: For Dropdown/RadioList fields, the exact values you can use
WORKFLOW:
Call get_pipelines to find the PipelineId
Call get_pipeline_custom_fields with the pipeline_id
Note all required fields and their valid options
Call create_pipeline_item with custom_fields: { "FieldName": "value", ... }
Example response interpretation: { "name": "Deal Stage", "required": true, "type": "Dropdown", "valid_options": ["Prospect", "Qualified", "Proposal"] } → You MUST include this field, value must be exactly "Prospect", "Qualified", or "Proposal"
Inputs: pipeline_id (required).
get_pipeline_itemGet Pipeline ItemA
Retrieve a single pipeline item by ID. Use this when you already have a PipelineItemId and need the record.
NOTE: search_pipeline_items returns the same full data for each match. Only use get_pipeline_item when you have an ID but not the data.
Inputs: pipeline_item_id (required).
get_pipeline_items_attached_to_contactGet Pipeline Items For ContactA
Retrieve all pipeline items for a specific contact. RETURNS FULL DATA: Each result includes all pipeline item fields - no need to call get_pipeline_item afterward. Returns items across all pipelines that the contact is in. Use count_only=true for accurate counts without returning the full result set.
Inputs: contact_id (required), page, count_only, max_results.
get_pipeline_item_schemaGet Pipeline Item SchemaA
Get complete field schema for creating/editing pipeline items.
Requires pipeline_id because each pipeline has different custom fields.
Returns ALL fields (both fixed system fields and custom fields) with:
name: The parameter name to use in create_pipeline_item/edit_pipeline_item
required: Whether this field must be provided
type: Field type (Text, Dropdown, etc.)
input_format: Exact format expected for the value
valid_options: For dropdowns, the exact values you can use
is_custom_field: Whether this is a custom field (true) or built-in (false)
WORKFLOW:
Call get_pipelines to find the pipeline_id and its status_ids
Call get_pipeline_item_schema with the pipeline_id
Use the schema to construct a valid create_pipeline_item call
Inputs: pipeline_id (required).
get_pipelinesGet PipelinesA
Retrieve all pipeline definitions for this LACRM account. Use this tool to discover available pipelines and their statuses before creating or editing pipeline items. Returns pipeline IDs, names, icons, and status definitions with sort order.
Each pipeline has multiple statuses that represent stages (e.g., "Lead", "Qualified", "Closed"). Use the PipelineId and StatusId values when creating or editing pipeline items.
WORKFLOW for pipeline items:
Call get_pipelines to find the PipelineId
Call get_pipeline_custom_fields with that pipeline_id to see required fields
Create/edit pipeline items with the correct PipelineId, StatusId, and custom_fields
Inputs: no named parameters.
get_pipeline_statusesGet Pipeline StatusesA
Get all statuses for a specific pipeline or all pipelines. Returns status IDs, names, active/closed state, colors, and creation dates.
Inputs: pipeline_id.
get_relationshipGet RelationshipA
Retrieve details about a specific relationship. Returns both contact IDs, the note, and metadata about both contacts.
Inputs: relationship_id (required).
get_relationships_attached_to_contactGet Relationships For ContactA
Retrieve all relationships for a specific contact. Returns all contacts linked to this contact with their relationship notes.
Inputs: contact_id (required), page, max_results.
get_taskGet TaskA
Retrieve a single task by ID. Use this when you already have a TaskId and need the record.
NOTE: search_tasks returns the same full data for each match. Only use get_task when you have an ID but not the data.
Inputs: task_id (required).
get_tasks_attached_to_contactGet Tasks For ContactA
Retrieve all tasks for a specific contact. RETURNS FULL DATA: Each result includes all task fields - no need to call get_task afterward. Use count_only=true for accurate counts without returning the full result set.
Inputs: contact_id (required), page, count_only, max_results.
get_teamGet TeamA
Get detailed information about a single team. Returns team name, creation date, and member user IDs.
Inputs: team_id (required).
get_teamsGet TeamsA
Get all teams accessible to the current user. Admins see all account teams; regular users only see teams they belong to.
Inputs: no named parameters.
get_usersGet UsersA
Retrieve all users in this LACRM account. Use this tool to discover user IDs when you need to assign contacts, tasks, or events to specific users. Returns user IDs, names, emails, and roles.
User IDs are required when creating events on a specific user's calendar or assigning tasks.
Inputs: no named parameters.
get_webhookGet WebhookA
Get detailed information about a single webhook. Returns endpoint URL, last send date, subscribed events, and archive status.
Inputs: webhook_id (required).
get_webhooksGet WebhooksA
Get all webhooks on the account. Optionally include archived webhooks.
Inputs: include_archived.
get_workflow_guideGet Workflow GuideA
START HERE: Get the workflow guide for using this LACRM MCP effectively.
This tool explains:
What schema tools to call BEFORE any create/edit operation
Required fields for contacts, companies, and pipeline items
Example workflows for common operations
How to interpret schema responses
Call this tool first when connecting to understand how to use the MCP correctly.
Inputs: no named parameters.
remove_contact_from_groupRemove Contact from GroupA
Remove a contact from a group in Less Annoying CRM. Use either group_id or group_name to identify the group (not both).
Inputs: contact_id (required), group_id, group_name.
search_contactsSearch ContactsA
Search for contacts and companies with filters and sorting. Use this tool to find contacts by name, email, or other criteria.
RETURNS FULL DATA: Each result includes all contact fields (name, email, phone, address, company, custom fields, timestamps, etc.) - no need to call get_contact afterward.
Supports:
Free text search across all fields
Filter by contacts only, companies only, or both
Filter by assigned user
Sort by name, date created, last update, or relevance
Advanced filters on standard and custom fields
IMPORTANT: For geographic searches (by state, city, zip), use advanced_filters with the address fields (AddressState, AddressCity, AddressZip, etc.) instead of search_terms. Free-text search_terms scans all fields and can be very slow on broad terms.
Use count_only=true for accurate counts on large datasets without returning the full result set. Use get_custom_fields to learn available custom field names for advanced filtering.
Inputs: page, sort_by, count_only, max_results, +5 more.
search_emailsSearch EmailsA
Search for logged emails with optional filters. Use this to find emails by date range, user, or contact.
RETURNS FULL DATA: Each result includes all email fields (sender, recipients, subject, body, timestamps, etc.) - no need to call get_email afterward.
Use count_only=true for accurate counts on large datasets without returning the full result set.
Inputs: page, date_end, contact_id, count_only, +5 more.
search_eventsSearch EventsA
Search for calendar events within a date range. Use this tool to find events by date, user, calendar, or contact.
RETURNS FULL DATA: Each result includes all event fields (name, dates, location, attendees, recurrence, etc.) - no need to call get_event afterward.
Supports filtering by:
Date range (start_date and end_date)
Specific users (by ID or name)
Specific calendars (by ID or name)
Specific contact
Use count_only=true for accurate counts on large datasets without returning the full result set.
Inputs: page, end_date, contact_id, count_only, +7 more.
search_notesSearch NotesA
Search for notes with optional date and user filters. Use this tool to find notes across all contacts or for specific users.
RETURNS FULL DATA: Each result includes all note fields (content, timestamps, linked contact, etc.) - no need to call get_note afterward.
Supports filtering by date range, user, and specific contact. Use count_only=true for accurate counts on large datasets without returning the full result set.
Inputs: page, date_end, contact_id, count_only, +4 more.
search_pipeline_itemsSearch Pipeline ItemsA
Search for pipeline items within a specific pipeline. Use this to find items by status, user, or custom field values.
RETURNS FULL DATA: Each result includes all pipeline item fields (status, contact info, custom fields, timestamps, etc.) - no need to call get_pipeline_item afterward.
Required: pipeline_id (use get_pipelines to find valid IDs). Supports advanced filters for custom fields. Supports name-based filters: use status_name_filter or user_name_filter instead of IDs. Use count_only=true for accurate counts on large datasets without returning the full result set.
Inputs: pipeline_id (required), page, sort_by, count_only, +7 more.
search_tasksSearch TasksA
Search for tasks within a date range. Use this tool to find tasks by date, user, contact, or completion status.
RETURNS FULL DATA: Each result includes all task fields (name, due date, description, completion status, linked contact, etc.) - no need to call get_task afterward.
Required: start_date, end_date. Supports filtering by completion status (Both, Incomplete, Complete). Supports name-based user filter: use user_name_filter instead of user_filter. Use count_only=true for accurate counts on large datasets without returning the full result set.
Inputs: end_date (required), start_date (required), page, contact_id, +6 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 88 tools
Most tools have clearly distinct purposes, but the sheer number of tools and overlapping retrieval patterns (e.g., get_pipeline_custom_fields vs get_custom_fields with pipeline filter, search_* vs get_*_attached_to_contact) create some potential for misselection. Descriptions are detailed enough to resolve most ambiguity.
The naming convention is overwhelmingly consistent: snake_case verb_noun (create/edit/delete/get/search) with resource names. Minor deviations like the bulk_* prefix and compound suffixes (e.g., _attached_to_contact, _in_group) are predictable and readable, so the overall pattern is strong.
With 88 tools, this is an extreme number for an MCP server, even considering the broad CRM domain. Many tools are convenience wrappers (e.g., get_X_attached_to_contact vs search_X) and schema/guide tools could be consolidated, making the surface feel bloated.
The tool set provides extensive CRUD coverage for contacts, companies, pipelines, statuses, notes, tasks, events, emails, groups, teams, custom fields, webhooks, and relationships. Notable minor gaps include no delete_file and no global file search, but core workflows are fully supported.
Maintenance
Related MCP Connectors
Unofficial remote MCP server for Less Annoying CRM: OAuth 2.1, read-only grants, 10 tools.
API-first CRM for LLMs - contacts, companies, deals and activities over a native MCP server.
MCP server for Getfly CRM — customers, opportunities, orders, tickets and tasks.
Marketo MCP server for AI. 130 tools to operate Marketo from Claude, Cursor, or ChatGPT.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceAn MCP server that provides 36 tools for interacting with the amoCRM (Kommo) API v4, covering leads, contacts, companies, and tasks. It supports full entity lifecycles, account analytics, and bulk operations with integrated OAuth 2.0 and rate limiting.2MIT
- AlicenseCqualityBmaintenanceMCP server for Pipedrive CRM providing 88 tools for full CRUD on deals, persons, organizations, activities, and more, with custom field resolution and safety guards.938MIT
- AlicenseBqualityDmaintenanceA comprehensive MCP server that connects AI assistants to GoHighLevel CRM, enabling management of contacts, conversations, calendars, pipelines, payments, and more through 60+ tools.6437 npm1MIT
- AlicenseNot gradedqualityDmaintenanceAn MCP server for interacting with Keap CRM, enabling contact and tag management, batch operations, custom fields, and advanced query optimization.MIT