Add Send4 remote MCP server
Maintainers usually reply within 1 day
Nobody has claimed this yet.
Assessment
- Difficulty
- 2/5
- Estimated time
- 1-3 hours
- Newbie friendliness
- 74/100
Research direction
Start by reading the registry inclusion heuristics and management docs linked in the issue, then inspect how existing catalog entries are represented in the repository. Add Send4 using its published tool definitions and setup guides as the source, and confirm the entry reflects the stated transport, authentication, and first-party service allowance.
Written by the indexing model from the issue text.
Description
MCP Server Information
Server Name: Send4
Repository URL: https://github.com/send4ai/send4-mcp-server
Brief Description: The official, first-party remote MCP server for Send4, AI SMS and email for sales and support teams. An assistant reads and changes a Send4 workspace (flows, campaigns, conversations, leads, meetings) as the signed-in person.
- Endpoint:
https://mcp.send4.ai/mcp - Transport: Streamable HTTP
- Authentication: OAuth 2.1 with dynamic client registration and PKCE (S256), discovered through the protected-resource metadata in the
401to an unauthenticatedinitialize.thv's loopback callback (http://localhost:8666/callback) is accepted. - Docs: https://send4.ai/support/ai-assistant-tools/
- Official MCP Registry:
ai.send4/mcp(active) - Tools: 64. Every tool's
tools/listdefinition is published in the repository above (tools/).
Workflow it enables
Ask why a lead's conversation went quiet (explain_conversation), read the thread (read_conversation), then improve the flow without touching the live one: duplicate_flow, change the copy with edit_flow, rehearse_flow it, check_flow it, and switch it on. Launching a campaign, switching a flow on or texting a typed number is two tools: a read-only preview_* that returns a summary for the person to confirm, then the write. Reporting tools (get_performance, get_drop_off, get_campaign_report) answer "how are we doing" with links back to the Send4 page.
Limitations, authentication and costs
- Needs a Send4 workspace on a plan or a started trial, with AI assistants switched on by a workspace admin. Each kind of change (flow editing, campaigns, conversations, team, mailboxes) has its own workspace switch, off by default, and the person picks permissions again on the consent screen.
- Changes are made as the signed-in person with their role's permissions and are recorded in the workspace audit log as made through an AI assistant.
- Rehearsing a flow uses the workspace's AI allowance; messages to customers are sent from the workspace's own numbers and mailboxes.
Source and licensing transparency
This is Send4's own first-party service. The hosted server implementation is proprietary. The linked repository is MIT-licensed and holds the setup guides and the published tool definitions, and it says so. This submission relies on the catalog criteria's first-party proprietary-service allowance; it does not present the hosted implementation as open source.
Basic Requirements
- Open Source: the hosted implementation is proprietary (first-party allowance, see above). The public repository is MIT.
- MCP Compliant: Streamable HTTP, OAuth 2.1 per the MCP authorization spec.
- Active Development: maintained by Send4; the repository's tool definitions were updated this week.
- Documentation: https://send4.ai/support/ai-assistant-tools/ and the repository README.
- Security Contact: private vulnerability reporting on the repository (
SECURITY.md).
Submitter Checklist
- I have read the MCP Server Registry Inclusion Heuristics
- This server meets the basic requirements listed above, relying on the first-party allowance for the hosted implementation
- I understand this will undergo automated and manual review based on Registry Management
- Dominant language
- Go
- Stars
- 26
- Forks
- 104
- Avg merge
- 1d 4h
- Merged PRs (30d)
- 69
Getting set up
- No Dockerfile or Docker Compose file
- No pull request template
- Read the contributing guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
More from stacklok/toolhive-catalog
-
needs-triage
Difficulty 2/5 1-3 hours Newbie friendliness 66/100
stacklok/toolhive-catalog#1967 ·
Maintainers usually reply within 1 day
-
needs-triage
Difficulty 2/5 1-3 hours Newbie friendliness 62/100
stacklok/toolhive-catalog#1929 · 1 comment ·
Maintainers usually reply within 1 day
-
needs-triage
Difficulty 2/5 1-3 hours Newbie friendliness 76/100
stacklok/toolhive-catalog#1918 ·
Maintainers usually reply within 1 day
-
needs-triage
Difficulty 1/5 1-3 hours Newbie friendliness 76/100
stacklok/toolhive-catalog#1914 ·
Maintainers usually reply within 1 day
-
needs-triage
Difficulty 2/5 1-3 hours Newbie friendliness 70/100
stacklok/toolhive-catalog#1909 ·
Maintainers usually reply within 1 day
All issues in stacklok/toolhive-catalog
Similar issues
-
area/networking kind/bug
Difficulty 2/5 1-3 hours Newbie friendliness 69/100
siderolabs/talos#14972 ·
Maintainers usually reply within 1 day
-
Difficulty 1/5 Under an hour Newbie friendliness 72/100
Maintainers usually reply within 1 day
-
kubectl wait outputs cryptic "error: unrecognized condition: []" when --for is omittedPossibly taken @muskan-creates352 claimed this today. Openkind/bug needs-triage
Difficulty 2/5 1-3 hours Newbie friendliness 84/100
kubernetes/kubectl#1910 · 1 comment ·
-
Difficulty 2/5 1-3 hours Newbie friendliness 66/100
unbound-force/gaze#353 ·
Maintainers usually reply within 1 day
-
bug cross-seed ready-for-human
Difficulty 2/5 1-3 hours Newbie friendliness 70/100
Maintainers usually reply within 1 day