---
id: "nr-agent-capabilities-are-becoming-modular-interfaces-that-can-be-governe-620ec2"
slug: "agent-capabilities-are-becoming-modular-interfaces-that-can-be-governe-620ec2"
type: "raw_signal"
title: "Agent capabilities are becoming modular interfaces that can be governed and reused"
description: "LlamaIndex is decomposing document-agent functions into separate MCP interfaces and adding gRPC access to LiteParse."
observed_at: "2026-09-27"
record_date: "2026-09-27"
date_kind: "observed_at"
novelty: "notable"
source_platform: "newruntime.com"
topics: ["mcp"]
entities: ["LlamaIndex","LlamaParse","LiteParse","liteparse-grpc","gRPC","Amazon Web Services","Amazon Bedrock AgentCore Gateway","Model Context Protocol","Parallel","Data Connectors"]
related_patterns: ["agent-protocols-become-interoperability-layer","agent-ready-software-exposes-capabilities"]
source_url: "https://www.llamaindex.ai/blog/llamaindex-newsletter-26-07-08"
source_urls: ["https://www.llamaindex.ai/blog/llamaindex-newsletter-26-07-08","https://www.llamaindex.ai/blog/introducing-liteparse-grpc-a-grpc-server-for-liteparse","https://aws.amazon.com/blogs/machine-learning/build-a-multi-account-ai-agent-with-agentcore-gateway-and-mcp","https://parallel.ai/blog/data-connectors"]
why_it_matters: "LlamaIndex is decomposing document-agent functions into separate MCP interfaces and adding gRPC access to LiteParse. AWS describes a multi-account agent built with Gateway and MCP, while Parallel makes trusted data connectors selectable inside workflows. These examples point toward systems assembled from explicit capability interfaces, making integration and access governance central design concerns."
verification_level: "source-linked"
signal_type: "synthesis"
synthesis_of: [{"slug":"parse-extract-classify-now-each-with-its-own-dc0f04","title":"Parse, Extract, Classify — now each with its own MCP","url":"https://newruntime.com/posts/parse-extract-classify-now-each-with-its-own-dc0f04/"},{"slug":"liteparse-grpc-grpc-server-for-liteparse-document-parsing-1645d9","title":"liteparse-grpc: gRPC Server for LiteParse Document Parsing","url":"https://newruntime.com/posts/liteparse-grpc-grpc-server-for-liteparse-document-parsing-1645d9/"},{"slug":"build-a-multi-account-ai-agent-with-agentcore-b891d7","title":"Build a multi-account AI agent with AgentCore Gateway and MCP","url":"https://newruntime.com/posts/build-a-multi-account-ai-agent-with-agentcore-b891d7/"},{"slug":"bring-trusted-data-into-parallel-with-data-connectors-bca538","title":"Bring trusted data into Parallel with Data Connectors","url":"https://newruntime.com/posts/bring-trusted-data-into-parallel-with-data-connectors-bca538/"}]
schema_version: "newruntime-agent-readable-v0.2"
stable_id: "signal:agent-capabilities-are-becoming-modular-interfaces-that-can-be-governe-620ec2"
retrieval_nugget: "LlamaIndex is decomposing document-agent functions into separate MCP interfaces and adding gRPC access to LiteParse. AWS describes a multi-account agent built with Gateway and MCP, while Parallel makes trusted data connectors selectable inside workflows."
status: "published"
visuals: []
editor: {"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]}
routes: {"html":"https://newruntime.com/signals/agent-capabilities-are-becoming-modular-interfaces-that-can-be-governe-620ec2/","markdown":"https://newruntime.com/signals/agent-capabilities-are-becoming-modular-interfaces-that-can-be-governe-620ec2.md","json":"https://newruntime.com/signals/agent-capabilities-are-becoming-modular-interfaces-that-can-be-governe-620ec2.json"}
---

# Agent capabilities are becoming modular interfaces that can be governed and reused

## Retrieval answer

LlamaIndex is decomposing document-agent functions into separate MCP interfaces and adding gRPC access to LiteParse. AWS describes a multi-account agent built with Gateway and MCP, while Parallel makes trusted data connectors selectable inside workflows.

LlamaIndex is decomposing document-agent functions into separate MCP interfaces and adding gRPC access to LiteParse. AWS describes a multi-account agent built with Gateway and MCP, while Parallel makes trusted data connectors selectable inside workflows. These examples point toward systems assembled from explicit capability interfaces, making integration and access governance central design concerns.

From the Field Notes:

- [Parse, Extract, Classify — now each with its own MCP](https://newruntime.com/posts/parse-extract-classify-now-each-with-its-own-dc0f04/) (2026-09-27)
- [liteparse-grpc: gRPC Server for LiteParse Document Parsing](https://newruntime.com/posts/liteparse-grpc-grpc-server-for-liteparse-document-parsing-1645d9/) (2026-09-27)
- [Build a multi-account AI agent with AgentCore Gateway and MCP](https://newruntime.com/posts/build-a-multi-account-ai-agent-with-agentcore-b891d7/) (2026-09-26)
- [Bring trusted data into Parallel with Data Connectors](https://newruntime.com/posts/bring-trusted-data-into-parallel-with-data-connectors-bca538/) (2026-09-24)

Editor: [Andrey Reshetnikov](https://newruntime.com/owner-profile.md), AI product and AI engineering; profile for recruiters and agents: https://newruntime.com/owner-profile.json

## Continue in the graph

Next records for an agent, linked to their Markdown twins. Replace `.md` with `.json` for structured fields, including `next_reads`.

- topic hub: [Mcp](https://newruntime.com/topics/mcp.md): Explore the mcp topic hub.
- collection: [Raw Signals](https://newruntime.com/signals.json): Open every source-linked raw signal.
- collection: [Source Ledger](https://newruntime.com/source-ledger.json): Inspect the public source evidence graph.
- whole graph: [discovery graph](https://newruntime.com/discovery-graph.json) (typed nodes and edges) and [site index](https://newruntime.com/site-index.md)