
ExecuFunction
- Updated March 10, 2026
- execufunction-mcp/mcp-server
ExecuFunction MCP is an MCP server that connects your IDE agent to tasks, calendar, knowledge, code indexing, and CRM on ExecuFunction.
About
ExecuFunction MCP (package @execufunction/mcp-server) turns your coding agent into a front end for an executive-function backend: tasks, scheduling, personal knowledge, searchable code context, and CRM-style contact tracking. founders who live in Claude Code or Cursor often lose thread between shipping, customer calls, and calendar blocks; this server reduces tab sprawl by exposing those primitives over MCP stdio. You point EXF_API_URL at your ExecuFunction deployment (e.g. execufunction.com) and authenticate with a personal access token from Settings → Developer. Journey-wide scope fits because the same connector supports Idea notes, Build implementation tracking, and Grow follow-ups—though the catalog shelf stays Build / agent-tooling as the primary install moment. Intermediate setup; you must operate or subscribe to the ExecuFunction service itself.
- Tasks, calendar, and knowledge base reachable from MCP tool calls
- Code indexing for context-aware answers inside the IDE
- Lightweight CRM for founder-led sales and follow-ups
- npm @execufunction/mcp-server v1.0.1 with npx runtime hint
- Auth via EXF_API_URL plus EXF_PAT personal access token
ExecuFunction by the numbers
- Data as of Jul 7, 2026 (Skillselion catalog sync)
claude mcp add --env EXF_API_URL=YOUR_EXF_API_URL --env EXF_PAT=YOUR_EXF_PAT mcp-server -- npx -y @execufunction/mcp-serverAdd your badge
Show developers this MCP server is listed on Skillselion. Paste this into your README.
| Package | @execufunction/mcp-server |
|---|---|
| Transport | STDIO |
| Auth | Required |
| Last updated | March 10, 2026 |
| Repository | execufunction-mcp/mcp-server ↗ |
What it does
Wire ExecuFunction into your IDE so the agent shares one executive-function layer for tasks, calendar, notes, code search, and lightweight CRM.
Who is it for?
Best when you already use or plan to host ExecuFunction and want one MCP bridge for productivity plus light CRM from the agent.
Skip if: Skip if you want only Git-native issues, or developers unwilling to create ExecuFunction PATs and depend on an external EXF API.
What you get
After registering the server with EXF_API_URL and EXF_PAT, your agent can read and update unified executive-function data from the same workflow where you code.
- Unified agent access to tasks, calendar, and knowledge
- Code-aware retrieval via ExecuFunction indexing
- CRM-style contact context during coding sessions
By the numbers
- Server version 1.0.1 (title ExecuFunction)
- Transport: stdio via npm @execufunction/mcp-server
- 2 required env vars: EXF_API_URL, EXF_PAT
README.md
ExecuFunction MCP Server
A Model Context Protocol server that exposes ExecuFunction tools to IDE clients like Cursor, Claude Desktop, and VS Code.
Quick Start
1. Create a Personal Access Token
- Go to ExecuFunction → Settings → Developer → Access Tokens
- Click "Create Token"
- Name it (e.g., "Cursor MCP")
- Select scopes:
mcp:*(or specific scopes likeprojects:read,tasks:write) - Save the token immediately - it's only shown once!
2. Configure Your MCP Client
Claude Desktop
Edit ~/Library/Application Support/Claude/claude_desktop_config.json:
{
"mcpServers": {
"execufunction": {
"command": "npx",
"args": ["@execufunction/mcp-server"],
"env": {
"EXF_API_URL": "https://execufunction.com",
"EXF_PAT": "exf_pat_your_token_here"
}
}
}
}
Cursor
Add to your Cursor MCP settings:
{
"execufunction": {
"command": "npx",
"args": ["@execufunction/mcp-server"],
"env": {
"EXF_API_URL": "https://execufunction.com",
"EXF_PAT": "exf_pat_your_token_here"
}
}
}
VS Code
Configure in your MCP extension settings.
3. Restart Your IDE
After configuration, restart your IDE to load the MCP server.
Available Tools
Projects
| Tool | Description | Mutates |
|---|---|---|
project_list |
List all projects with status filtering | No |
project_create |
Create a new project | Yes |
project_update |
Update project name, summary, status, emoji | Yes |
project_archive |
Archive a project (destructive) | Yes |
project_get_context |
Get full project context (tasks, notes, signals) | No |
Tasks
| Tool | Description | Mutates |
|---|---|---|
task_list |
List tasks with project/status/phase/effort filters | No |
task_get |
Get a single task with full details | No |
task_create |
Create a new task with priority, phase, effort, acceptance criteria | Yes |
task_update |
Update task fields (title, status, priority, phase, effort, scope) | Yes |
task_delete |
Delete a task (destructive) | Yes |
task_complete |
Mark a task as complete | Yes |
task_link_code |
Link a task to a code file/commit | Yes |
Knowledge / Notes
| Tool | Description | Mutates |
|---|---|---|
note_list |
List notes with type and project filters | No |
note_get |
Get a single note with full content | No |
note_search |
Semantic search across knowledge base | No |
note_create |
Create a new note (markdown) | Yes |
note_update |
Update note title, content, or type | Yes |
note_delete |
Delete a note (destructive) | Yes |
People
| Tool | Description | Mutates |
|---|---|---|
people_search |
Search contacts | No |
Calendar
| Tool | Description | Mutates |
|---|---|---|
calendar_list_events |
List calendar events for a date range | No |
calendar_create_event |
Create a new calendar event | Yes |
calendar_update_event |
Update a calendar event | Yes |
calendar_delete_event |
Delete a calendar event (destructive) | Yes |
Codebase Indexing
| Tool | Description | Mutates |
|---|---|---|
codebase_list |
List indexed repositories | No |
codebase_register |
Register a new repository for indexing | Yes |
codebase_status |
Check indexing status and stats | No |
codebase_snapshot_status |
Get latest index snapshot for a repository | No |
codebase_materialize_snapshot |
Download a snapshot archive | No |
codebase_index |
Full index: scan and upload all files | Yes |
codebase_index_incremental |
Incremental index: git-aware, changed files only | Yes |
codebase_delete |
Delete a repository and all indexed data (destructive) | Yes |
codebase_search |
Semantic search across indexed code | No |
Code History & Expertise
| Tool | Description | Mutates |
|---|---|---|
code_who_knows |
Find experts for a code area | No |
code_compute_expertise |
Refresh the expertise index | Yes |
code_history |
Get commit history for a repository | No |
git_blame_symbol |
Run git blame on a local file range | No |
Code Memories
| Tool | Description | Mutates |
|---|---|---|
code_memory_store |
Store a fact about the codebase | Yes |
code_memory_search |
Search stored code facts | No |
code_memory_list |
List all stored code memories | No |
code_memory_delete |
Delete a code memory (destructive) | Yes |
Vault / Secrets
| Tool | Description | Mutates |
|---|---|---|
vault_list |
List vault entries (metadata only) | No |
vault_create |
Store a new encrypted secret | Yes |
vault_read |
Decrypt and read a secret (audit-logged) | No |
vault_update |
Update vault entry metadata | Yes |
vault_search |
Search vault entries by name/description | No |
Entity Graph
| Tool | Description | Mutates |
|---|---|---|
entity_graph |
Traverse the entity relationship graph | No |
schema_introspect |
Discover the full data model and entity types | No |
Document Upload
| Tool | Description | Mutates |
|---|---|---|
upload_document |
Upload a PDF, Markdown, or text file into Knowledge | Yes |
Datasets (feature flag: DATASETS_ENABLED=true)
| Tool | Description | Mutates |
|---|---|---|
dataset_list |
List datasets | No |
dataset_create |
Create a dataset | Yes |
dataset_query |
Query records by filters/sorts | No |
dataset_mutate |
Create/update/delete records (destructive) | Yes |
dataset_schema_modify |
Add/update/delete fields (destructive) | Yes |
dataset_summarize |
Summarize schema and sample rows | No |
dataset_facets |
Value distributions for fields | No |
dataset_quality_check |
Null rates, duplicates, uniqueness violations | No |
dataset_aggregate |
Grouped metrics (count, avg, sum, etc.) | No |
dataset_bucket |
Bucket numeric/date fields into ranges | No |
dataset_rank |
Rank records by sorts or weighted formula | No |
dataset_analyze |
Generate natural-language insights | No |
dataset_compare |
Compare metrics across segments | No |
dataset_export |
Export records as CSV | No |
dataset_join_rows |
Self-join with alias-scoped fields | No |
dataset_compute_fields |
Compute derived columns (lag, diff, rolling) | No |
dataset_timeseries |
Time series analysis with transforms | No |
dataset_materialize_result |
Save derived result as a new dataset | Yes |
dataset_plot_result |
Validate chart payload from derived result | No |
Ontology (feature flag: DATASET_ONTOLOGY_ENABLED=true)
| Tool | Description | Mutates |
|---|---|---|
object_find |
Find objects by type and property filters | No |
object_links |
Traverse graph links for an object | No |
object_action_run |
Run a declarative action on an object (destructive) | Yes |
Usage Examples
1. Get project context and create a task
User prompt: "Get context for my auth project and create a task to fix the token refresh bug"
Tools invoked:
project_list— Lists projects to find the auth projectproject_get_context— Retrieves tasks, notes, and signals for the projecttask_create— Creates a new task with title, description, and project linkage
Result: The AI reads existing project context (open tasks, recent notes) to avoid duplicates, then creates a well-scoped task linked to the correct project.
2. Semantic code search
User prompt: "Find where we handle webhook signature verification"
Tools invoked:
codebase_search— Searches indexed code for "webhook signature verification"
Result: Returns ranked code chunks with file paths, line numbers, and surrounding context. The AI can then read the matched files to answer follow-up questions.
3. Knowledge search and note creation
User prompt: "Search for our deployment process and create a note summarizing the steps"
Tools invoked:
note_search— Searches the knowledge base for "deployment process"code_memory_search— Searches stored code facts for deployment-related memoriesnote_create— Creates a new note with a markdown summary of the deployment steps
Result: The AI synthesizes information from existing notes and code memories into a single reference note, linked to the relevant project.
Resources
The server also exposes project context bundles as MCP resources:
exf://projects/{id}/context- Full context bundle for a project
Environment Variables
| Variable | Required | Description |
|---|---|---|
EXF_API_URL |
Yes | ExecuFunction API URL |
EXF_PAT |
Yes | Personal Access Token |
Development
# Install dependencies
npm install
# Run in development mode
npm run dev
# Test with MCP Inspector
npm run inspect
# Build for production
npm run build
Security
- PATs are stored as SHA-256 hashes - plaintext is never stored
- Tokens can be revoked at any time from ExecuFunction Settings
- Use minimal scopes for your use case
- Never commit tokens to version control
Scopes
| Scope | Description |
|---|---|
mcp:* |
All MCP operations (recommended for IDE use) |
projects:read |
Read project data |
projects:write |
Create/update projects |
tasks:read |
Read tasks |
tasks:write |
Create/update/complete tasks |
knowledge:read |
Search/read notes |
knowledge:write |
Create notes |
calendar:read |
View calendar/free slots |
calendar:write |
Create calendar events |
people:read |
Search/view contacts |
people:write |
Create/update contacts |
Troubleshooting
"EXF_API_URL environment variable is required"
Make sure you've configured the env section in your MCP client config.
"Invalid token"
- Check that your token starts with
exf_pat_ - Verify the token hasn't been revoked
- Check the token hasn't expired
Tools not appearing
- Restart your IDE after configuration changes
- Check IDE logs for MCP errors
- Try running
npm run inspectto test the server directly
License
MIT
Recommended MCP Servers
How it compares
Hosted executive-function MCP hub, not a single-purpose GitHub or Notion-only integration.
FAQ
Who is ExecuFunction MCP for?
Developers using MCP clients who want agent access to ExecuFunction tasks, calendar, knowledge, code index, and CRM.
When should I use ExecuFunction MCP?
Use it whenever you work from the IDE across planning, building, and follow-ups and need the agent to see the same task and contact graph you use.
How do I add ExecuFunction MCP to my agent?
Install @execufunction/mcp-server via npx stdio, set EXF_API_URL to your instance, and set secret EXF_PAT from ExecuFunction Settings → Developer → Access Tokens.