Capsule CRM MCP server
Commit Nov 13, 2026Connect Claude to your Capsule CRM to manage contacts, opportunities, projects, tasks, and timeline activity using natural language.
Also known as soil-dev/capsulemcp
- Stars
- 5
- Tools
- —
- Downloads, 30 days
- —
- Latest version
- —
- Last commit
- Nov 13, 2026
- License
- Apache-2.0
What is Capsule CRM MCP?
Capsule CRM connects Claude to your Capsule CRM to manage contacts, opportunities, projects, tasks, and timeline activity using natural language.
Summary generated from the project's README
About Capsule CRM MCP server
Managing CRM data through natural language conversations is what capsulemcp enables for users of Capsule CRM. By connecting Claude Desktop, Claude Code, or web Projects via a Custom Connector, you can interact with your entire record graph including contacts, organisations, opportunities, projects, and tasks. The server provides 92 tools that allow for deep exploration of your data, ranging from simple searches to complex queries using structured filters with field and operator conditions.
Developers can choose between a local installation using stdio or a hosted setup using HTTP and OAuth. For those prioritizing data safety, the server includes a read-only mode via an environment variable and specific tool annotations that signal destructive actions. It also supports batch operations for mass updates and allows for file attachment management through read and write capabilities. Whether you are auditing deleted records or managing workflow tracks, this connector bridges the gap between your CRM and your AI assistant.
What you can do with it
- 1Querying CRM recordsAsk your AI assistant to find specific contacts or opportunities using natural language questions.
- 2Performing mass updatesUse batch tools to update multiple records at once within your CRM workflows.
- 3Executing complex data filtersApply structured filters with specific field and operator conditions to narrow down your CRM results.
- 4Managing project filesHandle file attachments by reading or writing files directly to your CRM records.
Written from the project's README. Every use case is checked against a quote from it.
Configuration
CAPSULE_API_TOKENCAPSULE_MCP_READONLY
| Name | Description | |
|---|---|---|
| CAPSULE_API_TOKEN | — | |
| CAPSULE_MCP_READONLY | — |
Automated checks
Ran Nov 14, 2026Full report →Not verified yet. A server needs a score of 80, no serious finding, and enough data for us to check. How checks work · What to fix for more points
- Source repository linked and reachablesoil-dev/capsulemcp is public and reachablegithub.com/soil-dev/capsulemcp ↗Pass
- Package names this repository as its sourceNot checked
- Build provenance (Sigstore attestation)Not checked
- Open source license (OSI)Apache-2.0spdx.org/licenses/Apache-2.0.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-11-13github.com/soil-dev/capsulemcp ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNot checked
- No critical advisory in the package or its dependenciesNot checked
- No hidden instructions to the model0 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNot checked
- Remote endpoint answers the MCP handshakeNot checked
README
View on GitHubcapsulemcp
A Model Context Protocol server for Capsule CRM. Connect Claude (Desktop, Code, or web Projects via Custom Connector) to your CRM and let it answer natural-language questions across the full record graph: contacts, organisations, opportunities, projects, tasks, and timeline activity. Beyond the basics it covers structured filters with field/operator conditions, saved searches with sort, workflow tracks (templates and instances), file attachments (read + write), audit of deleted records, and batch fetches up to 50 records per call.
- 92 tools across the Capsule resource graph (53 in read-only mode) — full read coverage plus careful, confirm-gated writes; 6 batched-write tools (
batch_*) for mass-update workflows - Two transports: stdio for local installs (Claude Desktop / Code), HTTP+OAuth for hosted Custom Connectors — with an unauthenticated
GET /healthtoken-health page for uptime monitoring - Read-only mode as a one-env-var flag; works alongside read-scoped Capsule tokens
- MCP tool annotations: 53 read tools carry
readOnlyHint: true, 8 destructive ones carrydestructiveHint: true— clients that honor these hints can auto-approve safe reads while still prompting for writes/destructive calls - Apache 2.0
Pick your install
| You want | Read this |
|---|---|
| Example questions to ask once the connector is running | EXAMPLES.md |
| To use it locally with Claude Desktop or Claude Code | INSTALL.md |
| To deploy it once and have your whole team use it via Claude.ai | DEPLOY.md |
| To wire it into n8n workflows | INTEGRATIONS-n8n.md |
| To contribute, debug, add a tool, or cut a release | HOWTO.md (procedures) · CONTRIBUTING.md (style & PR checks) |
| To understand what's intentionally not implemented (and why) | DESIGN.md |
| To see what performance work has been done (and what's next) | OPTIMIZATIONS.md |
| To see ideas for features that might land in future versions | IDEAS.md |
| To learn the surprising parts of Capsule's v2 API (with verbatim doc quotes) | NOTES-ON-CAPSULE-API.md |
For most individual users the install is a single JSON snippet pasted into Claude Desktop's config — see INSTALL.md.
Quick start (Claude Desktop)
-
Generate a Capsule API token: My Preferences → API Authentication Tokens → Generate, choose the Read scope for safety.
-
Add this to your
claude_desktop_config.json(~/Library/Application Support/Claude/claude_desktop_config.jsonon macOS):{ "mcpServers": { "capsule": { "command": "npx", "args": ["-y", "capsulemcp@2.5.0"], "env": { "CAPSULE_API_TOKEN": "<paste token here>", "CAPSULE_MCP_READONLY": "1" } } } } -
Restart Claude Desktop. The Capsule tools appear in the tool picker.
That's it. The first launch fetches the package from npm (a few seconds); subsequent launches are instant from the npx cache. The snippet pins an exact version on purpose: the connector runs with your Capsule token in its environment, so you should decide when new code runs with it — upgrade by changing the version after reading the release notes. Plain "capsulemcp" (unpinned) always runs the newest release instead; see INSTALL.md for the trade-off and how to verify a release's provenance. If you're tracking a fork or an unreleased branch, use the GitHub-ref form: "github:soil-dev/capsulemcp#v2.5.0" — same arguments, installs from a git clone rather than the npm registry. See INSTALL.md for the Claude Code path, manual install, and troubleshooting.
Tools
| Group | Read | Write |
|---|---|---|
| Parties (people/orgs) | search_parties, filter_parties, get_party, get_parties, list_employees, list_party_opportunities, list_party_projects, list_party_entries |
create_party, update_party, delete_party, add_party_email_address, remove_party_email_address_by_id, add_party_phone_number, remove_party_phone_number_by_id, add_party_address, remove_party_address_by_id, add_party_website, remove_party_website_by_id |
| Opportunities | search_opportunities, filter_opportunities, get_opportunity, get_opportunities, list_opportunity_entries, list_associated_projects |
create_opportunity, update_opportunity, delete_opportunity |
| Projects | search_projects, list_projects, filter_projects, get_project, get_projects, list_project_entries |
create_project, update_project, delete_project |
| Additional parties (multi-party deals) | list_additional_parties |
add_additional_party, remove_additional_party |
| Tasks | list_tasks, get_task, get_tasks |
create_task, update_task, complete_task, delete_task |
| Entries (notes / captured emails) | get_entry, list_entries |
add_note, update_entry, delete_entry |
| Attachments (file upload / download) | get_attachment |
upload_attachment |
| Activity feed (tenant-wide) | list_activities |
— |
| Audit (deleted records) | list_deleted_parties, list_deleted_opportunities, list_deleted_projects |
— |
| Pipelines & milestones (opportunities) | list_pipelines, list_milestones |
— |
| Boards & stages (projects) | list_boards, list_stages |
— |
| Tracks (workflow instances) | list_track_definitions, list_entity_tracks, get_track |
apply_track, update_track, remove_track |
| Saved filters | list_saved_filters, run_saved_filter |
— |
| Custom fields (schema) | list_custom_fields, get_custom_field |
— |
| Tags | list_tags |
add_tag, remove_tag_by_id, delete_tag_definition |
| Users & teams | list_users, get_current_user, list_teams |
— |
| Reference metadata | list_lost_reasons, list_activity_types, list_categories, list_goals, list_countries, list_currencies, get_site |
— |
Most record-list tools default perPage=25; reference-data tools default perPage=100 so small accounts usually fit in one response. All paginated tools cap perPage at 100 and return a nextPage cursor when more results exist. Many GET tools accept an embed parameter (e.g. tags,fields) — each tool's description enumerates its valid tokens (validated per resource; unknown tokens are rejected rather than silently ignored, and the caller-facing project token maps to Capsule's legacy kase on the wire).
The filter_* tools wrap Capsule's structured filter endpoint (POST /<entity>/filters/results) and accept an array of {field, operator, value} conditions ANDed together. Capsule's API does not support ad-hoc sort, so for "most recent X" questions filter by a date condition (e.g. addedOn is within last 7) and pick the highest id from the result — Capsule's numeric IDs are monotonically incrementing.
If you want sortable queries, use saved filters instead. Create the filter once in Capsule's web UI (it lets you set conditions, columns, and orderBy), then call run_saved_filter with its id. Use list_saved_filters to discover what's available.
Read-only mode
Set CAPSULE_MCP_READONLY=1 to disable every write/delete tool at the MCP layer (none of create_*, update_*, complete_task, add_note, or delete_* are registered). Pair it with a Capsule token that has the Read scope for defence in depth — your token's scope is the hard ceiling regardless of the env var.
Delete safety
Every whole-record delete_* tool, plus remove_track and remove_additional_party, requires confirm: true in its arguments. Without it, the schema rejects the call before any HTTP is made. Tool descriptions tell Claude to read the entity first and confirm with the user before invoking. The combined design — read-scoped token, read-only mode flag, schema-level confirm gate — means destructive actions are deliberate, not accidental.
License
Apache License 2.0 — Copyright 2026 Anton Arapov.
Capsule CRM MCP questions
How can I ensure the server only performs read operations?
You can set the CAPSULE_MCP_READONLY environment variable to 1 to disable all write and delete tools at the MCP layer.
How do I install this locally for Claude Desktop?
For local installation, add a JSON snippet to your Claude Desktop configuration file using npx to run the capsulemcp package.
Does the server support batch updates?
Yes, there are 6 batched-write tools available for mass-update workflows.
How are destructive actions prevented from happening accidentally?
Destructive tools require a 'confirm: true' argument, and the system is designed with read-scoped tokens and a read-only mode flag for defense in depth.