Innovation Lab Examples — Watchlist

MCP100 Assessment

Watchlist / Tracking

Why we’re tracking it

The examples repository evolves with Fetch.ai's agent tooling and protocol examples; a follow-up can verify whether its MCP examples remain runnable and clearly attributed.

Reviewed Oct 5, 2026 · Documentation review; complete setup workflow not independently tested

Best fit

Learning and prototyping multi-agent applications

What we know

Fetch.ai example repository covering uAgents, MCP, A2A, LLMs, payments, research, travel and deployment.

Maintenance / activity evidence

Observed Sep 1, 2026 (UTC)Merge pull request 184 from fetchai/feat/dynamic-ui-on-asi1

Tracking evidence observed Oct 5, 2026. These dated signals do not establish current maintenance. Reviewed enrichment confidence: high.

Activity source · commits ↗Activity source · releases ↗

Verification gaps / watch-outs

Installation and comprehensive security have not been independently audited.
Depends on each example's services. Writes: Some examples perform payments/shopping/deployment actions.
Example-specific.
Sensitive access: Credentials, Personal/payment data depending on example

This is a learning collection; assess each runnable example independently before providing credentials.

Security source · repository notice ↗Security source · policy file ↗

Full authority, access and evidence limits are available in Review context and Access & risk.

Popularity

1,149 repository stars

Stars observed Oct 6, 2026.

No canonical package metric applied.

All limitations / Review context

Have the MCP examples and their protocol dependencies stayed runnable and accurately documented in the next review?

The bounded assessment reviewed the official README, repository notices, security policy path, and security page for known material public-tracking blockers. No such blocker was identified. This is a public-tracking assessment, not an installation safety certification.

This is a learning collection; assess each runnable example independently before providing credentials.
Depends on each example's services.
Example-specific.
Varies by example/external service.
Reviewed write actions: Some examples perform payments/shopping/deployment actions
Sensitive access: Credentials, Personal/payment data depending on example
Installation, client compatibility and comprehensive security have not been independently audited. Authentication and access depend on the configured services.
No independent runtime, installation, or comprehensive security audit was performed.
No installation, runtime, client matrix, or complete tool-contract audit was performed in this review.
Each example has separate dependencies/credentials.
Some examples use paid external APIs.

Original activity observations

2026-09-01T15:08:56Z: Merge pull request 184 from fetchai/feat/dynamic-ui-on-asi1

Technical identity

github.com/fetchai/innovation-lab-examples

Exact implementation source: https://github.com/fetchai/innovation-lab-examples ↗
Reviewed resource type: Learning Resource
Repository identity: fetchai/innovation-lab-examples

Evidence & Sources

Evidence basis: Recorded source evidence
Setup runtime verification: Not independently runtime-tested by MCP100 for this setup workflow.

Reviewed Oct 5, 2026 · Latest source observation Oct 6, 2026

GitHub repository ↗
fetchai/innovation-lab-examples
Recorded repository material and project history.

Setup · Watchlist

Learning Resource setup

Publisher instructions.

Source evidence observed Oct 13, 2026.

Additional setup details required — see the specific gaps below.

Install / connect
Publisher instructions
Publisher-specific setup path. Follow prerequisites, then register or connect to your MCP host.
publisher documented install or connect · Publisher instructions · Review before use
```
git clone https://github.com/fetchai/innovation-lab-examples.git
```
Configure / authenticate
Publisher instructions
This repository is an EXAMPLES COLLECTION, not a single standalone MCP server. Select a concrete `mcp-agents` example and follow that subproject README and environment template.
Check connection
Suggested check
Run the selected example’s documented tool/list test; a repo checkout alone does not establish MCP connectivity.
Remove / uninstall / revoke
MCP100 setup guide
Stop the selected example process and remove its MCP client registration if one was created. No single universal MCP uninstall exists for the collection.

Official Documentation & Sources

What it does

Fetch.ai example repository covering uAgents, MCP, A2A, LLMs, payments, research, travel and deployment.

Capability: AI & Reasoning
Resource type: Learning Resource
Industry: Education & Research, Software & Technology
Best fit: Learning and prototyping multi-agent applications

Representative uses

Run quickstarter examples
Explore Agentverse deployment
Integrate LLMs and MCP
Build A2A teams/workflows

Limitations

Each example has separate dependencies/credentials.
Some examples use paid external APIs.

Reviewed access

Access & risk

Review the exact access boundary before connecting this MCP to accounts, credentials, or sensitive data.

Authentication: Example-specific.
Permissions: Depends on each example's services.
Data handling: Varies by example/external service.
Cost: usage_based
Risk and cautions: This is a learning collection; assess each runnable example independently before providing credentials.

Access scope and cautions

Write actions: Some examples perform payments/shopping/deployment actions
Sensitive access: Credentials Personal/payment data depending on example
Risk level: moderate

FAQ

Based on reviewed evidence as of 2026-10-06. Watchlist tracking is not a recommendation or a security certification.

Which tasks are documented for this implementation?

The reviewed tasks include: Run quickstarter examples; Explore Agentverse deployment; Integrate LLMs and MCP; Build A2A teams/workflows.

What setup and authentication are documented?

Recorded installation/entrypoint step: python3 -m venv .venv && source .venv/bin/activate && pip install -r requirements.txt. Prerequisites: Python 3.10+; pip; git. These are the documented setup details, not a claim that installation or client compatibility was independently tested. Authentication: Example-specific API keys.

Can it modify data or perform write operations?

Documented write actions include: Some examples perform payments/shopping/deployment actions. Recorded permission boundary: Depends on each example's services.

What data-handling boundary should I consider?

Varies by example/external service. Recorded sensitive-access context: Credentials; Personal/payment data depending on example.

What limitations and risks should I check before use?

This is a learning collection; assess each runnable example independently before providing credentials. Each example has separate dependencies/credentials. Some examples use paid external APIs. No independent runtime, installation, or comprehensive security audit was performed.

What cost model is recorded?

The reviewed cost model is usage based. This classification does not establish current prices, quotas or the cost of every downstream operation. Check the applicable service terms before authorizing paid actions.

Is this an official MCP?

Fetch.ai is listed as First-party MCP in MCP100’s current evidence.