How should ai be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this mcp.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

Crawler Summary

ai answer-first brief

Ambient AI Agent which works towards projects you give it, autonomous without you even asking for it. Multi-Step AI Agent with Google Workspace Integration This project is a sophisticated AI agent designed for complex, multi-step tasks that integrate with Google Workspace services like Gmail, Google Calendar, Google Docs, and Google Sheets. It features real-time streaming of its reasoning process, tool calls, and results, providing a transparent and interactive user experience. This project was built to demonstrate t Published capability contract available. No trust telemetry is available yet. Last updated 2/24/2026.

Freshness

Last checked 2/22/2026

Best For

Contract is available with explicit auth and schema references.

Not Ideal For

ai is not ideal for teams that need stronger public trust telemetry, lower setup complexity, or more explicit contract coverage before production rollout.

Evidence Sources Checked

editorial-content, capability-contract, runtime-metrics, public facts pack

Card Facts Snapshot Contract Trust

Claim this agent

Agent DossierGitHubSafety: 80/100

ai

MCPverified

Public facts

Change events

Artifacts

Freshness

Feb 22, 2026

Verifiededitorial-content1 verified compatibility signal

Published capability contract available. No trust telemetry is available yet. Last updated 2/24/2026.

Schema refs publishedTrust evidence available

Trust score

Unknown

Compatibility

MCP

Freshness

Feb 22, 2026

Vendor

Sriram Mk1

Artifacts

Benchmarks

Last release

0.1.0

Executive Summary

Key links, install path, and a quick operational read before the deeper crawl record.

Verifiededitorial-content

Summary

Published capability contract available. No trust telemetry is available yet. Last updated 2/24/2026.

View Source

Setup snapshot

git clone https://github.com/sriram-mk1/ambient-agent.git

1
Setup complexity is MEDIUM. Standard integration tests and API key provisioning are required before connecting this to production workloads.
2
Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.

Evidence Ledger

Everything public we have scraped or crawled about this agent, grouped by evidence type with provenance.

Verifiededitorial-content

Vendor (1)

Vendor

Sriram Mk1

profilemedium

Observed Feb 24, 2026Source link Provenance

Compatibility (2)

Protocol compatibility

MCP

contracthigh

Observed Feb 24, 2026Source link Provenance

Auth modes

mcp, api_key, oauth

contracthigh

Observed Feb 24, 2026Source link Provenance

Artifact (1)

Machine-readable schemas

OpenAPI or schema references published

contracthigh

Observed Feb 24, 2026Source link Provenance

Security (1)

Handshake status

UNKNOWN

trustmedium

Observed unknownSource link Provenance

Integration (1)

Crawlable docs

6 indexed pages on the official domain

search_documentmedium

Observed Apr 15, 2026Source link Provenance

Release & Crawl Timeline

Merged public release, docs, artifact, benchmark, pricing, and trust refresh events.

Self-declaredagent-index

Docs Update

Docs refreshed: Sign in to GitHub · GitHub

search_documentmedium

Fresh crawlable documentation was indexed for the official domain.

Observed Apr 15, 2026

Artifacts Archive

Extracted files, examples, snippets, parameters, dependencies, permissions, and artifact metadata.

Self-declaredGITHUB MCP

Extracted files

Examples

Snippets

Languages

typescript

Executable Examples

text

[User] -> [Next.js App] -> [AI Agent] -> [MCP Manager] -> [MCP Workers (Gmail, Calendar, etc.)] -> [Google APIs]

bash

git clone <repository-url>
    cd <repository-name>

bash

pnpm install
    cd mcps/gmail && pnpm install && cd ../..
    cd mcps/calendar && pnpm install && cd ../..
    cd mcps/docs && pnpm install && cd ../..
    cd mcps/sheets && pnpm install && cd ../..

bash

cd mcps/gmail
    pnpm run deploy # Assuming a deploy script is in package.json

bash

pnpm run dev

Docs & README

Full documentation captured from public sources, including the complete README when available.

Self-declaredGITHUB MCP

Docs source

GITHUB MCP

Editorial quality

ready

Full README

Multi-Step AI Agent with Google Workspace Integration

This project is a sophisticated AI agent designed for complex, multi-step tasks that integrate with Google Workspace services like Gmail, Google Calendar, Google Docs, and Google Sheets. It features real-time streaming of its reasoning process, tool calls, and results, providing a transparent and interactive user experience.

This project was built to demonstrate the power of the Model-Context Protocol (MCP), an open standard for building AI agents that can interact with tools and services in a standardized way.

Key Features
Architecture
Getting Started
Running the Application
Code Quality and Future Work
Detailed Documentation

Key Features

Multi-Step Execution: The agent can perform multiple actions to fulfill a single request, such as searching for emails and then creating a calendar event based on the results.
Real-Time Streaming: Observe the agent's thought process, tool calls, and results as they happen.
Google Workspace Integration: Seamlessly connect and control Gmail, Google Calendar, Google Docs, and Google Sheets.
Configurable Agent Behavior: Customize the agent's execution parameters, such as the maximum number of steps it can take.
User-Specific Authentication: Each user authenticates with their own Google account, ensuring that the agent acts on their behalf and with their permissions.

Architecture

The application is composed of two main parts:

Next.js Web Application: A modern web interface built with Next.js, React, and Tailwind CSS. This is the user-facing part of the application, where users can interact with the AI agent. It also serves the API endpoints that the frontend communicates with.
MCP Workers: A set of Cloudflare Workers that act as MCP servers for the various Google Workspace services. Each worker (e.g., for Gmail, Calendar) exposes a standardized set of tools that the AI agent can call. These workers are responsible for handling the logic of interacting with the Google APIs.

Diagram

[User] -> [Next.js App] -> [AI Agent] -> [MCP Manager] -> [MCP Workers (Gmail, Calendar, etc.)] -> [Google APIs]

Next.js App: Provides the UI and the main /api/chat endpoint.
AI Agent: The core logic that processes user requests, implemented using LangChain and Google's Gemini model.
MCP Manager: A component in the Next.js app that discovers and communicates with the MCP workers.
MCP Workers: Cloudflare Workers that wrap the Google APIs in an MCP-compliant interface.

Getting Started

Prerequisites

Node.js (v20 or later)
pnpm (or your preferred package manager)
A Google Cloud Platform project with the Gmail, Google Calendar, Google Docs, and Google Sheets APIs enabled.
Supabase project for authentication.
Cloudflare account for deploying the MCP workers.

Installation

Clone the repository:

git clone <repository-url>
cd <repository-name>

Install dependencies: This is a monorepo-style project, so you will need to install dependencies in the root and in each of the MCP worker directories.

pnpm install
cd mcps/gmail && pnpm install && cd ../..
cd mcps/calendar && pnpm install && cd ../..
cd mcps/docs && pnpm install && cd ../..
cd mcps/sheets && pnpm install && cd ../..

Configuration

Root .env.local file: Copy the .env.example to a new file named .env.local and fill in the required values for your Google Cloud, Supabase, and other services.
MCP Worker Configuration: Each MCP worker in the mcps/ directory has a wrangler.jsonc file. You will need to configure these with your Cloudflare account details. You will also need to set up the necessary secrets (e.g., for Google API access) for each worker.

Running the Application

Deploy the MCP Workers: For each worker in the mcps/ directory, run the following command to deploy it to Cloudflare:
```
cd mcps/gmail
pnpm run deploy # Assuming a deploy script is in package.json
```
Run the Next.js Application: From the root of the project, run:
```
pnpm run dev
```
The application will be available at http://localhost:3000.

Code Quality and Future Work

We have identified several areas for improvement in the current codebase, including refactoring duplicated code in the MCP workers and making the agent configuration persistent. For a detailed list of these items, please see the FIXES_NEEDED.md file.

Detailed Documentation

For more in-depth information about the AI agent's architecture, capabilities, and API, please refer to the following documents:

Agent Documentation: A deep dive into the agent's features, execution flow, and API endpoints.
Token Refresh System: An explanation of how the application manages and refreshes OAuth tokens for Google APIs.
Zep Memory Integration: Details on how the agent uses Zep for long-term conversation memory.
Implementation Summary: A summary of the technical implementation details.

Contract & API

Machine endpoints, protocol fit, contract coverage, invocation examples, and guardrails for agent-to-agent use.

Verifiedcapability-contract

Endpoints

Dossier API Snapshot API Contract API Trust API

Contract coverage

Status

ready

Auth

mcp, api_key, oauth

Streaming

Yes

Data region

global

Protocol support

MCP: verified

Requires: mcp, lang:typescript, streaming

Forbidden: none

Guardrails

Operational confidence: medium

Contract is available with explicit auth and schema references.

Trust confidence is not low and verification freshness is acceptable.

Protocol support is explicitly confirmed in contract metadata.

Invocation examples

curl -s "https://xpersona.co/api/v1/agents/mcp-sriram-mk1-ambient-agent/snapshot"

curl -s "https://xpersona.co/api/v1/agents/mcp-sriram-mk1-ambient-agent/contract"

curl -s "https://xpersona.co/api/v1/agents/mcp-sriram-mk1-ambient-agent/trust"

Reliability & Benchmarks

Trust and runtime signals, benchmark suites, failure patterns, and practical risk constraints.

Missingruntime-metrics

Trust signals

Handshake

UNKNOWN

Confidence

unknown

Attempts 30d

unknown

Fallback rate

unknown

Runtime metrics

Observed P50

unknown

Observed P95

unknown

Rate limit

unknown

Estimated cost

unknown

No benchmark suites or observed failure patterns are available.

Media & Demo

Every public screenshot, visual asset, demo link, and owner-provided destination tied to this agent.

Missingno-media

No screenshots, media assets, or demo links are available.

Related Agents

Neighboring agents from the same protocol and source ecosystem for comparison and shortlist building.

Self-declaredprotocol-neighbors

GITLAB_AI_CATALOGgitlab-mcp

Rank

A Model Context Protocol (MCP) server for GitLab

Traction

No public download signal

Freshness

Updated 2d ago

MCP

GITLAB_PUBLIC_PROJECTSgitlab-mcp

Rank

A Model Context Protocol (MCP) server for GitLab

Traction

No public download signal

Freshness

Updated 2d ago

MCP

GITLAB_AI_CATALOGrmcp-openapi

Rank

Expose OpenAPI definition endpoints as MCP tools using the official Rust SDK for the Model Context Protocol (https://github.com/modelcontextprotocol/rust-sdk)

Traction

No public download signal

Freshness

Updated 2d ago

MCP

GITLAB_AI_CATALOGrmcp-actix-web

Rank

An actix_web backend for the official Rust SDK for the Model Context Protocol (https://github.com/modelcontextprotocol/rust-sdk)

Traction

No public download signal

Freshness

Updated 2d ago

MCP

Machine Appendix

Contract JSON

{
  "contractStatus": "ready",
  "authModes": [
    "mcp",
    "api_key",
    "oauth"
  ],
  "requires": [
    "mcp",
    "lang:typescript",
    "streaming"
  ],
  "forbidden": [],
  "supportsMcp": true,
  "supportsA2a": false,
  "supportsStreaming": true,
  "inputSchemaRef": "https://github.com/sriram-mk1/ambient-agent#input",
  "outputSchemaRef": "https://github.com/sriram-mk1/ambient-agent#output",
  "dataRegion": "global",
  "contractUpdatedAt": "2026-02-24T19:46:37.963Z",
  "sourceUpdatedAt": "2026-02-24T19:46:37.963Z",
  "freshnessSeconds": 4431140
}

Invocation Guide

{
  "preferredApi": {
    "snapshotUrl": "https://xpersona.co/api/v1/agents/mcp-sriram-mk1-ambient-agent/snapshot",
    "contractUrl": "https://xpersona.co/api/v1/agents/mcp-sriram-mk1-ambient-agent/contract",
    "trustUrl": "https://xpersona.co/api/v1/agents/mcp-sriram-mk1-ambient-agent/trust"
  },
  "curlExamples": [
    "curl -s \"https://xpersona.co/api/v1/agents/mcp-sriram-mk1-ambient-agent/snapshot\"",
    "curl -s \"https://xpersona.co/api/v1/agents/mcp-sriram-mk1-ambient-agent/contract\"",
    "curl -s \"https://xpersona.co/api/v1/agents/mcp-sriram-mk1-ambient-agent/trust\""
  ],
  "jsonRequestTemplate": {
    "query": "summarize this repo",
    "constraints": {
      "maxLatencyMs": 2000,
      "protocolPreference": [
        "MCP"
      ]
    }
  },
  "jsonResponseTemplate": {
    "ok": true,
    "result": {
      "summary": "...",
      "confidence": 0.9
    },
    "meta": {
      "source": "GITHUB_MCP",
      "generatedAt": "2026-04-17T02:38:58.786Z"
    }
  },
  "retryPolicy": {
    "maxAttempts": 3,
    "backoffMs": [
      500,
      1500,
      3500
    ],
    "retryableConditions": [
      "HTTP_429",
      "HTTP_503",
      "NETWORK_TIMEOUT"
    ]
  }
}

Trust JSON

{
  "status": "unavailable",
  "handshakeStatus": "UNKNOWN",
  "verificationFreshnessHours": null,
  "reputationScore": null,
  "p95LatencyMs": null,
  "successRate30d": null,
  "fallbackRate": null,
  "attempts30d": null,
  "trustUpdatedAt": null,
  "trustConfidence": "unknown",
  "sourceUpdatedAt": null,
  "freshnessSeconds": null
}

Capability Matrix

{
  "rows": [
    {
      "key": "MCP",
      "type": "protocol",
      "support": "supported",
      "confidenceSource": "contract",
      "notes": "Confirmed by capability contract"
    }
  ],
  "flattenedTokens": "protocol:MCP|supported|contract"
}

Facts JSON

[
  {
    "factKey": "docs_crawl",
    "category": "integration",
    "label": "Crawlable docs",
    "value": "6 indexed pages on the official domain",
    "href": "https://github.com/login?return_to=https%3A%2F%2Fgithub.com%2Fopenclaw%2Fskills%2Ftree%2Fmain%2Fskills%2Fasleep123%2Fcaldav-calendar",
    "sourceUrl": "https://github.com/login?return_to=https%3A%2F%2Fgithub.com%2Fopenclaw%2Fskills%2Ftree%2Fmain%2Fskills%2Fasleep123%2Fcaldav-calendar",
    "sourceType": "search_document",
    "confidence": "medium",
    "observedAt": "2026-04-15T05:03:46.393Z",
    "isPublic": true
  },
  {
    "factKey": "protocols",
    "category": "compatibility",
    "label": "Protocol compatibility",
    "value": "MCP",
    "href": "https://xpersona.co/api/v1/agents/mcp-sriram-mk1-ambient-agent/contract",
    "sourceUrl": "https://xpersona.co/api/v1/agents/mcp-sriram-mk1-ambient-agent/contract",
    "sourceType": "contract",
    "confidence": "high",
    "observedAt": "2026-02-24T19:46:37.963Z",
    "isPublic": true
  },
  {
    "factKey": "auth_modes",
    "category": "compatibility",
    "label": "Auth modes",
    "value": "mcp, api_key, oauth",
    "href": "https://xpersona.co/api/v1/agents/mcp-sriram-mk1-ambient-agent/contract",
    "sourceUrl": "https://xpersona.co/api/v1/agents/mcp-sriram-mk1-ambient-agent/contract",
    "sourceType": "contract",
    "confidence": "high",
    "observedAt": "2026-02-24T19:46:37.963Z",
    "isPublic": true
  },
  {
    "factKey": "schema_refs",
    "category": "artifact",
    "label": "Machine-readable schemas",
    "value": "OpenAPI or schema references published",
    "href": "https://github.com/sriram-mk1/ambient-agent#input",
    "sourceUrl": "https://xpersona.co/api/v1/agents/mcp-sriram-mk1-ambient-agent/contract",
    "sourceType": "contract",
    "confidence": "high",
    "observedAt": "2026-02-24T19:46:37.963Z",
    "isPublic": true
  },
  {
    "factKey": "vendor",
    "category": "vendor",
    "label": "Vendor",
    "value": "Sriram Mk1",
    "href": "https://github.com/sriram-mk1/ambient-agent",
    "sourceUrl": "https://github.com/sriram-mk1/ambient-agent",
    "sourceType": "profile",
    "confidence": "medium",
    "observedAt": "2026-02-24T19:43:14.176Z",
    "isPublic": true
  },
  {
    "factKey": "handshake_status",
    "category": "security",
    "label": "Handshake status",
    "value": "UNKNOWN",
    "href": "https://xpersona.co/api/v1/agents/mcp-sriram-mk1-ambient-agent/trust",
    "sourceUrl": "https://xpersona.co/api/v1/agents/mcp-sriram-mk1-ambient-agent/trust",
    "sourceType": "trust",
    "confidence": "medium",
    "observedAt": null,
    "isPublic": true
  }
]

Change Events JSON

[
  {
    "eventType": "docs_update",
    "title": "Docs refreshed: Sign in to GitHub · GitHub",
    "description": "Fresh crawlable documentation was indexed for the official domain.",
    "href": "https://github.com/login?return_to=https%3A%2F%2Fgithub.com%2Fopenclaw%2Fskills%2Ftree%2Fmain%2Fskills%2Fasleep123%2Fcaldav-calendar",
    "sourceUrl": "https://github.com/login?return_to=https%3A%2F%2Fgithub.com%2Fopenclaw%2Fskills%2Ftree%2Fmain%2Fskills%2Fasleep123%2Fcaldav-calendar",
    "sourceType": "search_document",
    "confidence": "medium",
    "observedAt": "2026-04-15T05:03:46.393Z",
    "isPublic": true
  }
]

ai answer-first brief

Executive Summary

Evidence Ledger

Release & Crawl Timeline

Artifacts Archive

Docs & README

Multi-Step AI Agent with Google Workspace Integration

Table of Contents

Key Features

Architecture

Diagram

Getting Started

Prerequisites

Installation

Configuration

Running the Application

Code Quality and Future Work

Detailed Documentation

Contract & API

Reliability & Benchmarks

Media & Demo

Related Agents