run-mcp-local

A guide for running the FutureSearch HTTP MCP server locally with Docker Compose. MCP is a way for an AI assistant to call tools provided by another server.

In plain words
What is it for?
Use it to start, stop, troubleshoot, inspect logs for, or connect Claude to a local FutureSearch MCP server.
Why use it?
It explains how to start the server and Redis, avoid port conflicts, check that the service is healthy, and optionally make it reachable through a Cloudflare tunnel.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/futuresearch/futuresearch-python/run-mcp-local
Any agent
npx skills add futuresearch/futuresearch-python --skill run-mcp-local
Clone the repo
git clone --depth 1 https://github.com/futuresearch/futuresearch-python

Made for: Claude Code, Codex.

Per session 86 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,297 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 2 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.

ModelPer sessionOnce invoked
Fable 5 $0.00086 $0.02297
Opus 5 $0.00043 $0.01149
Sonnet 5 $0.00017 $0.00459
Haiku 4.5 $0.00009 $0.00230

Measured 2d ago against content hash 37e44533fa4e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

run-mcp-local scanned grade C with 2 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.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

curl -s https://<tunnel-url>/.well-known/oauth-authorization-server | python3 -m json.tool | head -5

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

Verify: `curl -s -o /dev/null -w "%{http_code}" http://localhost:8000/health` should return `200`.
.claude/skills/run-mcp-local/SKILL.md · 230 lines

How it starts

The opening of the file, as written. The whole thing — 230 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Running the FutureSearch MCP Server Locally

Two-container stack: mcp-server (FastAPI on :8000) and redis (on :6379), orchestrated by futuresearch-mcp/deploy/docker-compose.yaml with local overrides.

Pre-flight Checks

CRITICAL: Always check for stale processes on port 8000 before starting.

A leftover futuresearch-mcp --no-auth or similar process on the host will shadow the Docker container's port binding. All requests hit the stale process instead of the container — this can look like auth routes are broken, sheets tools are missing, etc.

# Check for anything on port 8000
lsof -i :8000

# Kill if needed
lsof -ti :8000 | xargs kill -9

Also check Docker is running:

docker info --format '{{.ServerVersion}}' || colima start

Quick Start

cd futuresearch-mcp/deploy

REDIS_PASSWORD=testpass \
MCP_SERVER_URL=http://localhost:8000 \
  docker compose \
    -f docker-compose.yaml \
    -f docker-compose.local.yaml \
  up -d --build

Verify: curl -s -o /dev/null -w "%{http_code}" http://localhost:8000/health should return 200.

Optional env vars

Pass these alongside REDIS_PASSWORD and MCP_SERVER_URL:

Env var Default Purpose
ENABLE_SHEETS_TOOLS false Register Google Sheets tools
TRUST_PROXY_HEADERS false Trust X-Forwarded-For (required behind tunnel)
EXTRA_ALLOWED_HOSTS (empty) Extra hostnames for DNS rebinding allowlist

These are templated in docker-compose.local.yaml as ${VAR:-default} — the container must be recreated (not just restarted) for env var changes to take effect.

Secrets

The .env file at futuresearch-mcp/deploy/.env contains production secrets (Supabase, API keys, upload secret). It is already present and should NOT be committed or overwritten.

REDIS_PASSWORD is intentionally NOT in .env — always pass it as an env var (testpass for local dev).

Worktrees

The .env file is gitignored and won't exist in worktrees. Symlink it:

Read the full file on GitHub · 230 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.

  1. 2d ago First seen · 230 lines · 86 tokens per session scan C 37e44533fa4e

Subscribe to this mod's changes

run-mcp-local is a skill published in the GitHub repository futuresearch/futuresearch-python (54 stars, last pushed 5d ago), licensed MIT. It adds 86 tokens to every session and 2,297 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

agent-harness-fault-injection

Use when an agent workflow needs deterministic recovery evidence for sandbox, MCP/tool, worker, checkpoint, memory, or orchestration failures.

sickn33/agentic-awesome-skills · 34 tokens

foundry-config-setup

Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.

microsoft/agent-framework · 65 tokens

azure-mgmt-apicenter-dotnet

Azure API Center SDK for .NET. Centralized API inventory management with governance, versioning, and discovery. Use for creating API services, workspaces, APIs, versions, definitions, environments, deployments, and metadata schemas. Triggers: "API Center", "ApiCenterService", "ApiCenterWorkspace", "ApiCenterApi", "API…

microsoft/skills · 97 tokens

azure-mgmt-botservice-dotnet

Azure Resource Manager SDK for Bot Service in .NET. Management plane operations for creating and managing Azure Bot resources, channels (Teams, DirectLine, Slack), and connection settings. Triggers: "Bot Service", "BotResource", "Azure Bot", "DirectLine channel", "Teams channel", "bot management .NET", "create bot".

microsoft/skills · 78 tokens

azure-communication-chat-java

Build real-time chat applications with Azure Communication Services Chat Java SDK. Use when implementing chat threads, messaging, participants, read receipts, typing notifications, or real-time chat features.

microsoft/skills · 41 tokens

bf-to-agents-sdk-dotnet-migration

Use when migrating a Bot Framework .NET SDK bot to Microsoft 365 Agents SDK. Triggered by projects that depend on packages: Microsoft.Bot.Builder or Microsoft.Bot.Builder.Integration.AspNet.Core that want to migrate to Agents SDK.

microsoft/Agents · 56 tokens