What is mcp-aggregator CLAUDE.md?

A project guide for an MCP Aggregator, a .NET application that connects AI tools and services through the Model Context Protocol.

Use it when building, running, configuring, or extending the aggregator's standard-input and HTTP servers, MCP tools, registry storage, and downstream connections.

It gives developers the project layout, build commands, configuration rules, and safeguards needed to change the system without breaking its communication or stored data.

How MarimerLLC/mcp-aggregator configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to MarimerLLC/mcp-aggregator. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/MarimerLLC/mcp-aggregator/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/MarimerLLC/mcp-aggregator

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/marimerllc/mcp-aggregator/claude-md.svg)](https://agentmods.dev/instructions/marimerllc/mcp-aggregator/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/marimerllc/mcp-aggregator/claude-md"><img src="https://agentmods.dev/badge/instructions/marimerllc/mcp-aggregator/claude-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 893 This file is loaded in full into every session.

When invoked 893 The same file — it is already loaded in full.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00893	$0.00893
Opus 5	$0.00447	$0.00447
Sonnet 5	$0.00179	$0.00179
Haiku 4.5	$0.00089	$0.00089

Measured 2d ago against content hash ed8b56f32586, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

mcp-aggregator CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 65 lines

How it starts

The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MCP Aggregator — Developer Guide

Project Structure

src/McpAggregator.Core/ — Shared library: models, services, MCP tools, storage
src/McpAggregator.StdioServer/ — Stdio MCP host (console app)
src/McpAggregator.HttpServer/ — HTTP/SSE MCP + REST API host (web app)
data/ — Runtime data directory (registry.json, skills/)

Build & Run

dotnet build                                          # Build all
dotnet run --project src/McpAggregator.HttpServer      # Run HTTP server
dotnet run --project src/McpAggregator.StdioServer     # Run stdio server

Critical Rules

StdioServer must NEVER write to stdout/stderr — those streams are the MCP transport. All logging goes to file/OTLP sinks only.
MCP tools are defined in Core — both hosts discover them via WithToolsFromAssembly(typeof(ConsumerTools).Assembly).
Registry persistence uses atomic writes — temp file + rename to prevent corruption.
Connections are lazy — downstream MCP servers are connected on first use, not at registration.

Configuration

All settings under McpAggregator section in appsettings.json, overridable via MCPAGGREGATOR__* env vars.

NuGet Packages

ModelContextProtocol 2.2.0 — MCP server hosting + DI
ModelContextProtocol.Core 2.2.0 — Client types (transitive)
ModelContextProtocol.AspNetCore 2.2.0 — HTTP transport (HttpServer only)

The 2.x line implements the MCP 2026-07-28 spec. Behaviors that matter here:

Stateless HTTP is the default (HttpServerTransportOptions.Stateless); ServeCommand still sets it explicitly. Stateful-only options now emit MCP9006.
Discovery-first negotiation — clients probe server/discover and fall back to the legacy initialize handshake for down-level servers. client.ServerInfo / ServerInstructions are populated either way.
SSE failures propagate the real exception (HttpRequestException, TimeoutException, genuine I/O) instead of a blanket IOException wrapper — ConnectionManager.ShouldRetry accounts for this.
Tool.inputSchema is required on deserialization; a downstream that omits it throws JsonException, which ToolIndex.GetToolsForServerAsync translates into a named AggregatorException.
Roots/Sampling/Logging are deprecated (MCP9005), Tasks moved to ModelContextProtocol.Extensions.Tasks, and AuthorizationRedirectDelegate is superseded by AuthorizationCallbackHandler (MCP9007). None of these are used by this project today.
Microsoft.Extensions.* must be 10.0.10+ — the SDK pins Hosting.Abstractions to that floor.

Read the full file on GitHub · 65 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

2d ago Changed · +7 lines · +138 tokens per session ed8b56f32586
6d ago First seen · 58 lines · 755 tokens per session scan A 72a58123c297

Subscribe to this mod's changes

mcp-aggregator CLAUDE.md is an instructions file published in the GitHub repository MarimerLLC/mcp-aggregator (25 stars, last pushed 2d ago), licensed MIT. It adds 893 tokens to every session, about $0.0045 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

mcp-aggregator: Instructions file for Claude Code