continuum-tools-mcp

continuum-tools-mcp is a skill for Claude Code from shyftlabs/continuum. It costs 94 tokens per session (3,102 once invoked), scanned A, original, Apache-2.0.

A tools guide for connecting Continuum agents to MCP servers, which provide local or remote tools through a shared protocol.

In plain words
What is it for?
Use it to connect filesystem or remote API tools, choose a local or HTTP transport, filter available tools, and capture structured tool results.
Why use it?
It gives agents access to external actions and data sources while letting you control which tools and context they receive.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

Good fit Use it to connect filesystem or remote API tools, choose a local or HTTP transport, filter available tools, and capture structured tool results.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/shyftlabs/continuum/continuum-tools-mcp
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.

Any agent
npx skills add shyftlabs/continuum --skill continuum-tools-mcp
Clone the repo
git clone --depth 1 https://github.com/shyftlabs/continuum

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.

agentmods badge for continuum-tools-mcp

README.md
[![agentmods](https://agentmods.dev/badge/skills/shyftlabs/continuum/continuum-tools-mcp/github.svg)](https://agentmods.dev/skills/shyftlabs/continuum/continuum-tools-mcp)
Your own site
<a href="https://agentmods.dev/skills/shyftlabs/continuum/continuum-tools-mcp"><img src="https://agentmods.dev/badge/skills/shyftlabs/continuum/continuum-tools-mcp/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for continuum-tools-mcp

Your own site · 80×15
<a href="https://agentmods.dev/skills/shyftlabs/continuum/continuum-tools-mcp"><img src="https://agentmods.dev/badge/skills/shyftlabs/continuum/continuum-tools-mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 94 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,102 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 5.1 $0.00094 $0.03102
Opus 5.5 $0.00038 $0.01241
Sonnet 5.5 $0.00019 $0.00620
Haiku 4.5 $0.00009 $0.00310

Measured 13d ago against content hash fd8e326780e1, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

continuum-tools-mcp 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 13d 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/skills/continuum-tools-mcp/SKILL.md · 333 lines

How it starts

The opening of the file, as written. The whole thing — 333 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Continuum MCP / Tools Skill

Authoritative source: docs/tools.md.


Imports

from continuum.tools import (
    MCPServerStdio, MCPServerSse, MCPServerStreamableHttp,
    ToolExecutor, MCPUtil,
    ToolContextConfig, ToolContextVariable,
    create_static_tool_filter, ToolFilterContext,
    MCPToolArtifact, RunArtifacts,
)
# `ToolExecutorConfig` is not in the `continuum.tools` namespace —
# import it from the executor module directly.
from continuum.tools.executor import ToolExecutorConfig

Three transports

Transport When
MCPServerStdio Local subprocess MCP server
MCPServerSse Legacy SSE-based remote
MCPServerStreamableHttp Recommended for any modern remote
local = MCPServerStdio(
    {"command": "npx",
     "args": ["-y", "@modelcontextprotocol/server-filesystem", "./data"]},
    name="local",
)
await local.connect()                       # ALWAYS connect first

remote = MCPServerStreamableHttp(
    {"url": "https://example.com/mcp",
     "headers": {"Authorization": "Bearer …"}},
    name="remote",
)
await remote.connect()

Quickest agent wiring

from continuum.agent import BaseAgent, AgentRunner

agent = BaseAgent(
    name="tool-agent",
    instructions="Use the tools to answer.",
    mcp_servers=[local, remote],            # tool discovery is automatic
)
resp = await AgentRunner().run(agent, "...")

Manual ToolExecutor (for shared executors / restrictions)

executor = ToolExecutor(
    tool_registry={
        local: None,                        # None = expose all of this server's tools
        remote: ["search", "ingest"],       # restrict
    },
    config=ToolExecutorConfig(
        max_concurrent_calls=5,
        rate_limit_per_second=10.0,
        timeout_seconds=30.0,
    ),
)
await executor.initialize()                  # REQUIRED when constructed with tool_registry

agent = BaseAgent(name="…", instructions="…", tool_executor=executor)

Read the full file on GitHub · 333 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. 13d ago Changed · +7 lines fd8e326780e1
  2. 1mo ago First seen · 326 lines · 94 tokens per session scan A 2326157c3daf

Subscribe to this mod's changes

continuum-tools-mcp is a skill published in the GitHub repository shyftlabs/continuum (84 stars, last pushed 14d ago), licensed Apache-2.0. It adds 94 tokens to every session and 3,102 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-09-03.