cor-mcp-setup

Setup and usage instructions for an MCP server exposing Project COR’s REST API, a web interface for projects, tasks, clients, time tracking, and teams. It documents email/password and API-key authentication.

In plain words
What is it for?
Installing the COR server, connecting it to an agent, choosing an authentication method, and accessing Project COR through local or remote MCP transports.
Why use it?
It provides the installation, credentials, transport, and agent-connection details needed to make Project COR data available to an MCP-compatible agent.

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/fxckcode/mcp-cor/cor-mcp-setup
Any agent
npx skills add fxckcode/mcp-cor --skill cor-mcp-setup
Clone the repo
git clone --depth 1 https://github.com/fxckcode/mcp-cor

Made for: Claude Code, Codex.

Per session 47 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 903 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 $0.00047 $0.00903
Opus 5 $0.00023 $0.00451
Sonnet 5 $0.00009 $0.00181
Haiku 4.5 $0.00005 $0.00090

Measured yesterday against content hash bdbfbd86ec9c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

cor-mcp-setup 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 yesterday.

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.

- `uv` installed (`curl -LsSf https://astral.sh/uv/install.sh | sh`)

Makes network callslowCapability

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

- `uv` installed (`curl -LsSf https://astral.sh/uv/install.sh | sh`)
skills/cor-mcp-setup/SKILL.md · 122 lines

How it starts

The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.

COR MCP Server

An MCP server that exposes the full Project COR REST API (61 tools) for use from any MCP-compatible agent (Hermes Agent, Claude Desktop, Cursor, Claude Code, etc.).

Prerequisites

  • Python 3.11+
  • uv installed (curl -LsSf https://astral.sh/uv/install.sh | sh)
  • COR credentials (email + password or API key + client secret)

Quick Install

cd /path/to/cor-mcp-server
uv sync

Configuration

Copy .env.example to .env and set ONE authentication mode:

Mode A: Email + Password (personal use)

[email protected]
COR_PASSWORD=your_password
COR_API_URL=https://api.projectcor.com/v1

Mode B: API Key + Client Secret (server-to-server)

COR_API_KEY=your_api_key
COR_CLIENT_SECRET=your_client_secret
COR_API_URL=https://api.projectcor.com/v1

The server auto-detects which mode you configured. Email/password takes priority when both are set.

Running

# stdio (default — for MCP agents)
uv run cor-mcp-server

# SSE/HTTP (for remote access)
uv run cor-mcp-server --transport sse --host 0.0.0.0 --port 8000

Hermes Agent Integration

Add this to your ~/.hermes/config.yaml under mcp_servers:

mcp_servers:
  cor:
    command: "uv"
    args: ["run", "--directory", "/absolute/path/to/cor-mcp-server", "python", "-m", "cor_mcp_server"]
    env:
      COR_EMAIL: "[email protected]"
      COR_PASSWORD: "your_password"
      COR_API_URL: "https://api.projectcor.com/v1"
    timeout: 180
    connect_timeout: 60

Then do /reload-mcp in the Hermes session.

Available Tools (all prefixed with cor_)

Entity Count Key Tools
Projects 14 list, create, update, delete, collaborators, costs, profitability
Tasks 10 search, create, update, labels, collaborators, my pending
Clients 6 list, create, update, delete, fees
Contracts 5 list, create, positions
Time Tracking 5 log hours, search, change status, accept suggested
Team & Users 8 profile, users, teams, working time
Messaging 4 project/task messages
Ratecards 3 list, get, create
Allocations 3 by project, save, delete
Products 2 list, create
Labels 1 by entity type

Read the full file on GitHub · 122 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. yesterday First seen · 122 lines · 47 tokens per session scan C bdbfbd86ec9c

Subscribe to this mod's changes

cor-mcp-setup is a skill published in the GitHub repository fxckcode/mcp-cor (0 stars, last pushed 1mo ago), licensed MIT. It adds 47 tokens to every session and 903 once invoked, about $0.0002 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 2026-08-31.

Related

Other skills, from other repositories

plane-workflow

Create, update, audit, standardize, label, and organize Plane work items with the Plane Workflow MCP tools. Use when a user asks to create a Plane task or issue, turn a brief into a ticket, manage modules, or improve a Plane backlog.

amirhosseinkz/plane-workflow-mcp · 56 tokens

agile-development

ServiceNow Agile Development 2.0 — the rmteam → rmsprint → rmstory → rmepic model, the state and point values ServiceNow actually accepts, how a story is attached to a sprint, and the reporting tools (board, burndown, velocity, capacity, standup, retrospective).

serac-labs/serac · 68 tokens

linear-oneshot

Find one-shottable WaniWani Linear tickets and scope them for autonomous execution. Use when the user says "triage one-shots", "find easy tickets", "find simple tickets", "one-shot triage", "qualify WAN-123", "scope WAN-123", "is this ticket one-shottable", or wants to label simple Linear tickets an agent can…

WaniWani-AI/sdk · 89 tokens

discover-work

Deep research across codebase, GitHub issues, discussions, project board, and architecture docs to discover new tasks, gaps, technical debt, and improvement ideas. Trigger when user says: discover work, find tasks, what needs doing, audit codebase, find gaps, technical debt audit, backlog discovery, brainstorm tasks…

Destrayon/Connapse · 77 tokens

building-glamorous-tuis

Build terminal UIs with Charmbracelet (Bubble Tea, Lip Gloss, Gum). Use when: Go TUI, shell prompts/spinners, "make CLI prettier", adaptive layouts, async rendering, focus state machines, sparklines, heatmaps, kanban boards, SSH apps.

nikships/skills-registry · 65 tokens

ulc-loop

Start a Unified Loop Controller session via Ralph Wiggum. Autonomously works through backlog, dispatches agents, and explores via QD when idle.

Kastalien-Research/thoughtbox · 35 tokens