hive-mcp

hive-mcp is a skill for Claude Code from hive-intel/hive-sdk. It costs 106 tokens per session (1,885 once invoked), scanned A, original, MIT.

A setup and troubleshooting guide for connecting Hive's MCP service to AI clients such as Claude, ChatGPT, Cursor, and Codex. It explains the shared endpoint, connection method, and interactive or headless sign-in options.

In plain words
What is it for?
Use it to install, configure, verify, or debug Hive MCP, including OAuth sign-in, API-key access, endpoint settings, and connection checks.
Why use it?
It helps identify the right configuration for each client and diagnose missing tools, authentication errors, or confusion between hosted and local connections.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions Codex; mentions Gemini CLI.

Part of the hive plugin — 17 skills, 1 MCP server shipped together

Good fit Use it to install, configure, verify, or debug Hive MCP, including OAuth sign-in, API-key access, endpoint settings, and connection checks.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/hive-intel/hive-sdk/hive-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 hive-intel/hive-sdk --skill hive-mcp
Clone the repo
git clone --depth 1 https://github.com/hive-intel/hive-sdk

Made for: Claude Code.

Or install hive, the plugin that ships this one along with the rest of its 17 skills, 1 MCP server.

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 hive-mcp

README.md
[![agentmods](https://agentmods.dev/badge/skills/hive-intel/hive-sdk/hive-mcp/github.svg)](https://agentmods.dev/skills/hive-intel/hive-sdk/hive-mcp)
Your own site
<a href="https://agentmods.dev/skills/hive-intel/hive-sdk/hive-mcp"><img src="https://agentmods.dev/badge/skills/hive-intel/hive-sdk/hive-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 hive-mcp

Your own site · 80×15
<a href="https://agentmods.dev/skills/hive-intel/hive-sdk/hive-mcp"><img src="https://agentmods.dev/badge/skills/hive-intel/hive-sdk/hive-mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 106 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,885 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 warn 7 Sept 2026
SkillSpector: 5 findings, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium MCP Rug Pull · line 44
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
  • medium MCP Rug Pull · line 129
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
  • medium MCP Rug Pull · line 60
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
  • medium Excessive Agency · line 108
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
  • medium MCP Rug Pull · line 126
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
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 $0.00106 $0.01885
Opus 5 $0.00053 $0.00942
Sonnet 5 $0.00021 $0.00377
Haiku 4.5 $0.00011 $0.00188

Measured 8d ago against content hash f721df978830, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

hive-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 8d 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.

skills/hive-mcp/SKILL.md · 170 lines

How it starts

The opening of the file, as written. The whole thing — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.

hive-mcp — Add Hive to an MCP Client

Walk the user through adding Hive's MCP endpoint to whichever AI client they're using. The endpoint is the same everywhere; only the config file path and shape vary per client.

Universal facts

  • MCP URLhttps://mcp.hiveintelligence.xyz/mcp
  • Transport — Streamable HTTP (single endpoint, supports both POST and GET; SSE is legacy)
  • Auth — after hosted OAuth activation, interactive remote clients use URL-only OAuth 2.1 discovery and browser consent. Headless backends may send Authorization: Bearer <HIVE_API_KEY> from secret storage; x-api-key is a legacy fallback. Check protected-resource metadata before claiming the interactive path is live.
  • Cost — one credit per material endpoint execution regardless of payload size. Search, schema lookup, task-result validation, category listing, tools/list, and resource reads cost zero credits. 4xx errors don't consume credits; 5xx errors are refunded.

After hosted OAuth activation, interactive MCP setup does not require the user to create or paste an API key. Route to hive-build-onboarding for direct CLI, REST, headless access, or the temporary fallback while OAuth metadata is not available.

Fast path — one command

If the user is on a machine with multiple MCP-capable clients and just wants Hive everywhere:

npx -y -p hive-intelligence@latest hive init --all

This writes URL-only config for supported local clients and prints the native UI steps for clients such as Claude and ChatGPT. When protected-resource metadata is live, each interactive client opens Hive browser authorization on first connect. Until then, do not present that path as installed; use the trusted API-key fallback or wait for activation. Codex and headless OpenAI Responses API setups remain explicit: Codex uses codex mcp add followed by codex mcp login, while the headless Responses API uses an environment-backed credential.

For agents that support standalone skills, install the Hive skills after MCP is connected so the agent also knows the workflow layer:

Read the full file on GitHub · 170 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 8d ago First seen · 170 lines · 106 tokens per session scan A f721df978830

Subscribe to this mod's changes

hive-mcp is a skill published in the GitHub repository hive-intel/hive-sdk (18 stars, last pushed 2d ago), licensed MIT. It adds 106 tokens to every session and 1,885 once invoked, about $0.0005 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.

Related

Other skills, from other repositories

palisade-security-scanner

Onchain security scanner on Robinhood Chain — scan token approvals, detect honeypots, analyze contracts for rugpull indicators, check liquidity locks, and score contract safety. Use when a user asks an agent to evaluate, scan, or check a token or wallet before trading, swapping, signing an approval, or investing. 18…

palisadescan/palisade · 97 tokens

design-mcp-server

Design the tool surface, resources, and service layer for a new MCP server. Use when starting a new server, planning a major feature expansion, or when the user describes a domain/API they want to expose via MCP. Produces a design doc at docs/design.md that drives implementation.

cyanheads/coingecko-mcp-server · 62 tokens

add-tool

Scaffold a new MCP tool definition. Use when the user asks to add a tool, create a new tool, or implement a new capability for the server.

cyanheads/coingecko-mcp-server · 35 tokens

api-linter

MCP definition linter rules reference. Use when bun run lint:mcp or bun run devcheck reports a lint error or warning (format-parity, schema-is-object, name-format, server-json-, etc.) and you need to understand the rule, its severity, and how to fix it. Every rule ID the linter emits has an entry in this doc.

cyanheads/coingecko-mcp-server · 86 tokens

api-context

Canonical reference for the unified Context object passed to every tool and resource handler in @cyanheads/mcp-ts-core. Covers the full interface, its RequestContext base, all sub-APIs (ctx.log, ctx.state, ctx.requestInput, ctx.inputs, ctx.enrich, ctx.content), and when to use each.

cyanheads/coingecko-mcp-server · 79 tokens

api-canvas

DataCanvas primitive reference — a Tier 3 SQL/analytical workspace for tabular MCP servers, backed by DuckDB. Use when registering tables from upstream APIs, running ad-hoc SQL across them, and exporting results. Covers the acquire → register → query → export flow, per-table TTL, the token-sharing pattern for…

cyanheads/coingecko-mcp-server · 85 tokens