Add e2a integration#1766
Merged
Merged
Conversation
✅ Deploy Preview for adk-docs-preview ready!
To edit notification comments on pull requests, go to your Netlify project configuration. |
|
Thanks for your pull request! It looks like this may be your first contribution to a Google open source project. Before we can look at your pull request, you'll need to sign a Contributor License Agreement (CLA). View this failed invocation of the CLA check for more information. For the most up to date status, view the checks section at the bottom of the pull request. |
jiashuoz
force-pushed
the
add-e2a-integration
branch
from
7265a15 to
505eb07
Compare
Contributor
Author
|
@googlebot I signed the CLA! |
Contributor
Author
|
@googlebot I signed the CLA! |
jiashuoz
force-pushed
the
add-e2a-integration
branch
from
505eb07 to
a431a71
Compare
e2a is an authenticated email gateway for AI agents — SPF/DKIM-verified inbound, optional human-in-the-loop approval before outbound mail ships. Distributed as an MCP stdio server via npx -y @e2a/mcp-server, exposing 11 tools for inbox management, threaded replies, and HITL approval flows. Source: https://github.com/Mnexa-AI/e2a/tree/main/mcp npm: https://www.npmjs.com/package/@e2a/mcp-server
jiashuoz
force-pushed
the
add-e2a-integration
branch
from
a431a71 to
869aa3e
Compare
2 tasks
jiashuoz
added a commit
to Mnexa-AI/e2a
that referenced
this pull request
May 18, 2026
…sets (#89) * docs(mcp): add runnable end-to-end examples for ADK, LangChain, OpenAI Agents Three self-contained agent demos under mcp/examples/ that drive the published @e2a/mcp-server over stdio. Each has README + requirements.txt + a minimal agent.py — runnable with one pip install and an LLM key. Doubles as living docs for the README snippets and as the canonical "does the published package work?" verification harness. Verified end-to-end: spawned npx -y @e2a/mcp-server@0.1.1 from the LangChain example, confirmed all 11 tools load with correct schemas. ADK and OpenAI Agents use the same stdio wire-up so high confidence, not directly invoked. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * docs(mcp): add system prompt to LangChain example Parity with the ADK and OpenAI Agents examples — tells the model to use whoami first and prefer reply_to_message over send_email for threaded replies. Without it, the LangChain agent had no guidance on tool selection. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * docs(mcp): warn about webhook signing secret in cloud mode + stage brand assets The `create_agent` MCP tool exposes `agent_mode: 'cloud'` to the LLM, but the description (and the README's tool table) didn't mention that cloud-mode users must HMAC-verify webhook deliveries against E2A_WEBHOOK_SECRET. Without this, an LLM walking a user into cloud mode leaves them with an unverified webhook handler. Add the warning to: - mcp/src/tools/agents.ts — the source-of-truth tool description that every MCP host surfaces - mcp/README.md — npm registry page The adk-docs PR (google/adk-docs#1766) was updated separately with the same warning, plus a link to the existing runnable example at examples/adk-cloud-webhook. Also stage brand assets at assets/ (square logo, 256px variant, wordmark) for npm/Smithery/dashboard/etc. usage. Audit of the rest of the docs confirms webhook signing is already well-covered in the root README and both SDK READMEs. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
koverholt
requested changes
May 18, 2026
Collaborator
koverholt
left a comment
koverholt
left a comment
There was a problem hiding this comment.
Thanks for the PR and contribution! All content LGTM since you followed the template, thanks for that. I left one comment about shortening the catalog description. Once that is done, this is good to merge and publish to our integration catalog.
Collaborator
|
Also you can ignore the failing CI check for external links, all of your links are passing and the failure is unrelated to this PR. We will address that separately. |
koverholt
approved these changes
May 18, 2026
Collaborator
koverholt
left a comment
koverholt
left a comment
There was a problem hiding this comment.
Thanks for the edit and for the contribution! Merging.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Adds e2a as an MCP-based integration under
docs/integrations/e2a.md.e2a is an authenticated email gateway built for AI agents. Inbound mail is SPF/DKIM-verified before reaching your agent. Outbound mail can be held in a pending queue for human approval — optionally with reviewer edits to subject, body, or recipients — before it actually ships.
The integration is distributed as a stdio MCP server (
@e2a/mcp-serveron npm, published with provenance) and exposes 11 tools across three groups:whoami,list_agents,create_agentsend_email,reply_to_message,list_messages,get_messagelist_pending_messages,get_pending_message,approve_pending_message,reject_pending_messageFiles
docs/integrations/e2a.md— integration page following the CONTRIBUTING.md template (frontmatter, use cases, prerequisites, Python + TypeScript snippets, tool table, configuration table, resources)docs/integrations/assets/e2a.png— 256×256 PNG logoVerification
The example wired in the documentation has been run end-to-end against the published
@e2a/mcp-server@0.1.1:Agentwithgemini-flash-latest+ the exactMcpToolsetconfig in the snippet chained two tool calls (whoami→list_agents) against realapi.e2a.devand synthesized a correct natural-language answer.MultiServerMCPClient.get_tools()and ADK's tool discovery.CLA
Mnexa AI has signed the Google Corporate CLA. Authorized contributor: @jiashuoz.