AgentLater MCP server
Commit Nov 14, 2026Allows AI agents to schedule HTTP requests, poll for job completion, and retrieve results or webhooks in later sessions.
Also known as thachp/agentlater
- Stars
- 0
- Tools
- —
- Downloads, 30 days
- —
- Latest version
- 1.0.0
- Last commit
- Nov 14, 2026
- License
- MIT
What is AgentLater MCP?
AgentLater allows AI agents to schedule HTTP requests, poll for job completion, and retrieve results or webhooks in later sessions.
Summary generated from the project's README
About AgentLater MCP server
Developers building autonomous agents can use AgentLater to schedule HTTP requests that occur outside of an active chat session. This hosted MCP server allows an agent to trigger background tasks, poll for job completion, or receive webhooks and retrieve results in a later session. It is designed for agents that need to perform time-delayed work, such as generating a report in fifteen minutes without keeping the user session open.
To use this service, connect an MCP client that supports remote Streamable HTTP and MCP OAuth to the gateway URL. Authentication is handled through a standard OAuth flow rather than manual API keys. Once connected, agents can manage their work using tools like schedule_http, queue_http, and create_cron. The system also provides an inbox via read_inbox and ack_inbox to handle incoming results. A trial period includes 1,000 delivery attempts over 7 days, and users can manage credentials securely using the set_secret tool.
What you can do with it
- 1Schedule delayed background tasksAn agent can schedule a POST request to a webhook to run after a specific delay.
- 2Poll for long-running job completionAn agent can monitor a status URL to wait until a specific job has finished.
- 3Retrieve results in new sessionsAn agent can check its inbox to read results from previous HTTP deliveries.
- 4Manage and retry scheduled workA developer can use tools to inspect, stop, or retry specific tasks.
Written from the project's README. Every use case is checked against a quote from it.
How to install AgentLater MCP
Formats verified 10 Nov 2026Add to CursorAdd to GooseInstall AgentLater MCP in Claude Code
$ claude mcp add --transport http agentlater https://gateway.agentlater.io/mcpInstall AgentLater MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"agentlater": {
"url": "https://gateway.agentlater.io/mcp"
}
}
}Install AgentLater MCP in VS Code
.vscode/mcp.json
{
"servers": {
"agentlater": {
"type": "http",
"url": "https://gateway.agentlater.io/mcp"
}
}
}Install AgentLater MCP in VS Code CLI
$ code --add-mcp '{"name":"agentlater","type":"http","url":"https://gateway.agentlater.io/mcp"}'Install AgentLater MCP in Codex
$ codex mcp add agentlater --url https://gateway.agentlater.io/mcpInstall AgentLater MCP in Codex config.toml
~/.codex/config.toml
[mcp_servers.agentlater] url = "https://gateway.agentlater.io/mcp"
Install AgentLater MCP in Gemini CLI
$ gemini mcp add -s user --transport http agentlater https://gateway.agentlater.io/mcpInstall AgentLater MCP in Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"agentlater": {
"url": "https://gateway.agentlater.io/mcp",
"type": "http"
}
}
}Automated checks
Ran Nov 15, 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 reachablethachp/agentlater is public and reachablegithub.com/thachp/agentlater ↗Pass
- Package names this repository as its sourceNot checked
- Build provenance (Sigstore attestation)Not checked
- Open source license (OSI)MITspdx.org/licenses/MIT.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-11-14github.com/thachp/agentlater ↗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 handshakeHTTPS endpoint answered 401 (sign-in required)Pass
README
View on GitHubAgentLater
Let an AI agent make an HTTP request later, and check whether it happened.
AgentLater is a hosted Model Context Protocol (MCP) server for agents that need to schedule HTTP work, wait for a job, or retrieve results in a later session. It sends requests and records delivery outcomes; it does not run the agent itself.
What agents can do
| Need | Tools |
|---|---|
| Send a request later or in the background | schedule_http, queue_http (optionally serialize related requests in a named queue) |
| Repeat a request or poll until a job finishes | create_cron, watch_http |
| Receive webhooks and read results in a later session | create_hook, read_inbox, ack_inbox |
| Inspect, stop or retry work | get_task, list_tasks, cancel_task, redrive_task |
| Use credentials or trigger an agent workflow when results arrive | set_secret, set_wake |
See the full tool reference for arguments, limits and delivery semantics. A wake URL must belong to something that can start an agent run; inbox events alone do not resume a chat.
Connect an MCP client
Use a client that supports remote Streamable HTTP and MCP OAuth. Add a remote server or custom
connector named agentlater with this URL:
https://gateway.agentlater.io/mcp
For clients using an mcpServers JSON configuration with HTTP transport, the configuration is:
{
"mcpServers": {
"agentlater": {
"type": "http",
"url": "https://gateway.agentlater.io/mcp"
}
}
}
Configuration formats vary by client; use its remote-server settings if it does not accept this shape. The endpoint and transport are also declared in server.json.
Authentication: complete the OAuth flow opened by your client and click Connect on the
AgentLater consent page. There is no account to create or API key to paste into the configuration;
the client manages OAuth tokens. Each approved connection owns a separate project and trial.
Call create_project once after connecting (calling it again returns the same project): the trial
includes 1,000 delivery attempts for 7 days. Use get_project to inspect the balance and get_payment_link
when more attempts are needed.
For Claude Code, you can instead install the plugin, which includes the hosted server configuration and a skill for using the tools:
/plugin marketplace add thachp/agentlater
/plugin install agentlater@agentlater
See the plugin README for installation and migration details. Autonomous integrations can also use Agent Auth at the gateway; that identity and its project are separate from a hosted MCP connection.
A2A
An agent that speaks the Agent2Agent protocol (version 1.0,
JSON-RPC) can schedule one-off deliveries and read, list and cancel them, signed in with Agent Auth and no
human login. Start from the Agent Card at https://gateway.agentlater.io/.well-known/agent-card.json.
# in a checkout, after npm ci
node apps/gateway/examples/a2a-client.mjs https://gateway-staging.agentlater.io
a2a-client.mjs is a complete client in one file: it reads the Agent
Card, registers, makes its project, schedules a delivery and polls it to its end. Outside a checkout, copy the file and
npm install @a2a-js/sdk@1.3.0 @auth/agent@0.6.2. It keeps its keys in
~/.agentlater/ (mode 0600). The auth sequence, payload schema, task states, errors and what is not offered
through A2A (crons, watches, hooks, secrets, payments, streaming, push notifications, callbacks, lanes) are in
the A2A docs and PRODUCT.md.
Example: trigger a background job through a webhook
A common use is calling your application's job endpoint after a delay—for example, generating an export in 15 minutes without keeping the agent session open.
After connecting, ask your agent:
Create my AgentLater project, then POST to my export webhook in 15 minutes with
{"report": "daily-sales", "format": "csv"}. Use my stored webhook token, capture the response, and put the delivery result in my inbox.
The agent calls create_project with {}. If the endpoint requires a bearer token, first call
set_secret with these arguments, replacing the placeholder with your endpoint's actual token
and the host with your own:
{
"name": "WEBHOOK_TOKEN",
"value": "<your-webhook-token>",
"allowed_hosts": ["api.example.com"]
}
Then call schedule_http with the following arguments. Replace the example URL with your own
public HTTPS job endpoint. body is a JSON-encoded string, not an object.
{
"url": "https://api.example.com/jobs/export",
"method": "POST",
"headers": {
"Content-Type": "application/json",
"Authorization": "Bearer {{secret:WEBHOOK_TOKEN}}"
},
"body": "{\"report\":\"daily-sales\",\"format\":\"csv\"}",
"delay": "15m",
"idempotency_key": "daily-sales-export-001",
"capture": true,
"callback_url": "inbox"
}
Use a new idempotency_key for each intended job; reusing the same key and request returns the
original task. Your endpoint should also deduplicate deliveries using RunLater-Task-Id because
delivery retries can reach it more than once. For an endpoint without authentication, omit the
secret setup and the Authorization header.
Save the returned task_id and inspect it with get_task({"task_id": "<returned task_id>"}).
In a later session, call get_project with {}, then read_inbox with {} if inbox_unread
is above zero. After handling the events, call ack_inbox({"up_to": 1}), replacing 1 with the
last seq you handled. These are MCP tool names and argument objects, not shell commands.
No public callback URL is needed to receive the delivery report in the inbox. If the endpoint
returns 202 Accepted, that confirms it accepted the job; use watch_http on its status URL
when you also need to wait for the export to finish.
Delivery is at least once; succeeded means the destination returned HTTP 2xx. Destinations must
be public HTTPS URLs, not localhost or private IP addresses. For authenticated requests, store the
credential with set_secret and use {{secret:NAME}} in a header instead of pasting it into a request.
Limits and troubleshooting
- Schedule at most 7 days ahead. Cron expressions use UTC and run at most hourly; watches poll every 5 minutes to 24 hours. Captured responses keep the first 16 KiB of the body for 7 days after the task finishes.
project_not_found: callcreate_projecton the current connection before scheduling.budget_exhaustedortrial_expired: inspectget_projectand useget_payment_linkfor more attempts. Each delivery attempt, poll and URL callback attempt consumes budget; inbox delivery is free.- Connection or sign-in fails: confirm the URL ends in
/mcpand the client supports both Streamable HTTP and OAuth. A client limited to local stdio servers needs a supported bridge; see the Agent Auth bridge configuration. - No result yet: inspect
get_taskwith the returnedtask_idfor its status and attempt history. Read the inbox using the same connection that scheduled the task; a new connection has a separate project.
Documentation and compatibility
AgentLater was formerly RunLater. Existing runlater plugin connections retain their own projects;
installing the agentlater plugin creates a separate connection rather than moving existing work.
Some internal package names and delivery headers (such as RunLater-Task-Id) retain the old name
for compatibility.
The specs are PRODUCT.md (what it does), ARCHITECTURE.md (how it's built) and DESIGN.md (how it should feel, to agents and to people). The pre-rebuild implementation was removed at cutover; it is in git history before this change.
Layout
| Path | What | Stack |
|---|---|---|
apps/api |
Private task API: ledger, scheduling, delivery | Rust · workers-rs |
apps/gateway |
Public entry for agents: Agent Auth, capabilities, MCP, A2A | TypeScript Worker |
apps/web |
agentlater.io landing, docs and payment page | Next.js · OpenNext |
apps/receiver |
Staging-only fixture the journey and the A2A run deliver to | TypeScript Worker |
crates/core |
Task domain, no Cloudflare deps | Rust |
crates/egress |
Destination policy and request signing | Rust |
packages/contracts |
Capability definitions, and the OpenAPI contract between gateway and API | TypeScript · OpenAPI 3.1 |
packages/tsconfig |
Shared TypeScript config | |
plugins/agentlater |
Claude Code plugin: the hosted MCP server and an agentlater skill |
Markdown · JSON |
plugins/runlater |
The old plugin, deprecated and frozen so existing installs keep working | Markdown · JSON |
Everything deploys to Cloudflare Workers, with staging and production environments in each app's wrangler.jsonc (apps/receiver has staging only); see docs/DEPLOY.md.
Develop
Requires Rust (pinned in rust-toolchain.toml), Node 22+, and cargo install worker-build --version 0.8.7 --locked.
npm install
cargo test && npm run typecheck && npm test
Every check CI runs, in one command (-- --fast skips the e2e suites):
npm run verify
The rules the code keeps, and the lints that enforce them, are in CODING_STANDARDS.md.
npm run dev -w @runlater/gateway
npm run dev -w @runlater/web
License
The code is MIT. Using the hosted service at agentlater.io is covered by its Terms of Service and Privacy Policy.
AgentLater MCP questions
How do I add AgentLater MCP to Claude Code?
Run claude mcp add --transport http agentlater https://gateway.agentlater.io/mcp in your terminal. Add --scope user to make it available in every project.
How do I add AgentLater MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
What is the trial limit for AgentLater?
The trial includes 1,000 delivery attempts for a duration of 7 days.
Can I use secrets for authenticated HTTP requests?
Yes, you can use the set_secret tool to store credentials and reference them in headers using the {{secret:NAME}} syntax.
How far in advance can I schedule a task?
You can schedule tasks up to a maximum of 7 days ahead.