Marcora MCP server
Commit Nov 14, 2026Provides a context layer for go-to-market teams to manage brand voice, positioning, and product facts for AI-driven marketing content generation.
Also known as ccromp/marcora-mcp, mcp
- Stars
- 0
- Tools
- —
- Downloads, 30 days
- —
- Latest version
- 1.0.5
- Last commit
- Nov 14, 2026
- License
- MIT
What is Marcora MCP?
Marcora provides a context layer for go-to-market teams to manage brand voice, positioning, and product facts for AI-driven marketing content generation.
Summary generated from the project's README
About Marcora MCP server
Marcora provides a centralized context layer for go-to-market teams to maintain brand voice, positioning, and product facts. It functions as a single source of truth that AI clients like Claude, ChatGPT, Cursor, and VS Code can access to ensure generated marketing content remains accurate and on-brand. The service is a hosted remote MCP server that uses streamable HTTP for transport and requires either OAuth 2.0 or an API token for authentication.
Users can manage a Brand Foundation and a Reference Library containing buyer personas, competitive analysis, and product documentation. The server includes specialized tools for creating content blueprints, managing projects, and executing multi-step workflows. It also features content grounding capabilities to check document claims against the established context library. For teams using Anthropic clients, the Marcora AI Workflows skill can be installed to help the agent understand the specific object model and tool sequencing required for complex marketing tasks.
What you can do with it
- 1Maintain Brand ConsistencyEnsure all AI-generated marketing materials adhere to your specific company voice and writing style.
- 2Automate Content ProductionUse reusable playbooks and workflows to generate marketing content at scale.
- 3Standardize Content CreationCreate and use blueprints to act as templates for consistent content generation.
Written from the project's README. Every use case is checked against a quote from it.
How to install Marcora MCP
Formats verified 10 Nov 2026Add to CursorAdd to GooseInstall Marcora MCP in Claude Code
$ claude mcp add --transport http mcp https://mcp.marketcore.ai/Install Marcora MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"mcp": {
"url": "https://mcp.marketcore.ai/"
}
}
}Install Marcora MCP in VS Code
.vscode/mcp.json
{
"servers": {
"mcp": {
"type": "http",
"url": "https://mcp.marketcore.ai/"
}
}
}Install Marcora MCP in VS Code CLI
$ code --add-mcp '{"name":"mcp","type":"http","url":"https://mcp.marketcore.ai/"}'Install Marcora MCP in Codex
$ codex mcp add mcp --url https://mcp.marketcore.ai/Install Marcora MCP in Codex config.toml
~/.codex/config.toml
[mcp_servers.mcp] url = "https://mcp.marketcore.ai/"
Install Marcora MCP in Gemini CLI
$ gemini mcp add -s user --transport http mcp https://mcp.marketcore.ai/Install Marcora MCP in Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"mcp": {
"url": "https://mcp.marketcore.ai/",
"type": "http"
}
}
}Automated checks
Ran Nov 14, 2026Full report →Not verified yet. A server needs a score of 80, no serious finding, and enough data for us to check. How checks work · What to fix for more points
- Source repository linked and reachableccromp/marcora-mcp is public and reachablegithub.com/ccromp/marcora-mcp ↗Pass
- Package names this repository as its sourceNot checked
- Build provenance (Sigstore attestation)Not checked
- Open source license (OSI)MITspdx.org/licenses/MIT.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-11-14github.com/ccromp/marcora-mcp ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNot checked
- No critical advisory in the package or its dependenciesNot checked
- No hidden instructions to the model0 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNot checked
- Remote endpoint answers the MCP handshakeHTTPS endpoint answered 401 (sign-in required)Pass
README
View on GitHubMarcora MCP Server
Marcora is the context layer for go-to-market teams: your positioning, brand voice, and product facts in one source of truth that your AI tools read from.
Learn more: marcora.ai
About
This is the public documentation repository for Marcora's hosted MCP server. The server itself is a commercial, closed-source remote service. This repo provides metadata, connection instructions, tool documentation, and support resources.
| Type | Hosted remote MCP server |
| Implementation | Closed-source (commercial) |
| Transport | Streamable HTTP |
| Authentication | OAuth 2.0 or API token |
| Status | Production |
What It Does
Marcora is the context layer for go-to-market teams. Build your source of truth once: a Brand Foundation (positioning, brand voice, and writing style) plus a Reference Library of product docs, buyer personas, competitive analysis, and messaging. Claude, ChatGPT, and any AI tool that supports MCP connections read from it, so what you write stays on-brand and accurate.
Marcora was formerly called MarketCore.
Marcora's MCP server enables AI clients to:
- Manage brand and company context and reference materials
- Create and manage blueprints for content generation
- Generate marketing content from context and blueprints
- Organize work with projects and collections
- Browse and import community blueprints and templates
- Plan content on the plans board and produce it, individually or from reusable playbooks
- Automate recurring work with reusable, multi-step workflows
- Share content externally and export to Word
Connection
Server URL (OAuth): https://mcp.marcora.ai
Authentication options:
- OAuth 2.0 (recommended for interactive clients) — connect using
https://mcp.marcora.ai - API Token (for non-interactive environments) — generate a key at Integration Settings and connect to the same URL (
https://mcp.marcora.ai), passing the key in anAuthorization: Bearer <your-api-key>header. The server negotiates the right transport automatically.
Quickstart
Add to your MCP client config:
{
"mcpServers": {
"marcora": {
"url": "https://mcp.marcora.ai"
}
}
}
See docs/quickstart.md for setup instructions for Claude, ChatGPT, Claude Desktop, Cursor, and VS Code.
The Marcora AI Workflows Skill (recommended)
The Marcora AI Workflows Anthropic Skill ships alongside this server. It teaches your AI client Marcora's mental model, the right tool sequencing, the questions to ask the user before acting, and the pitfalls to avoid — so the agent stops misfiring on tasks that look ambiguous from tool descriptions alone.
| Skill | What it covers | Source |
|---|---|---|
Marcora AI Workflows (marcora-mcp) |
Object model (content, blueprints, projects, context items); content-generation patterns; the 4-layer context model; project-brief mechanics; the content plans board and playbooks; building reusable multi-step workflows; and choosing between similar tools | skill/marcora-mcp/ |
Your AI client picks the skill up on demand based on the task.
Install with the skills CLI
npx skills add ccromp/marcora-mcp
This installs the marcora-mcp skill for Claude Code and other agents that read SKILL.md skills. To preview first, run npx skills add ccromp/marcora-mcp --list.
Download
Get the .skill file from the latest release:
marcora-mcp.skill— the Marcora skill (a zip archive containingSKILL.mdand its bundled reference files).
Install
Claude Code:
# Download and unzip into your skills directory
mkdir -p ~/.claude/skills
unzip ~/Downloads/marcora-mcp.skill -d ~/.claude/skills/
Restart Claude Code. The skill loads automatically on any matching task.
Claude Desktop:
Import the .skill file via Claude Desktop's Skills folder. See Anthropic's Skills documentation for the current path on your platform.
ChatGPT, Cursor, and other non-Anthropic clients:
These clients don't directly support Anthropic Skills (yet). Workaround: unzip the .skill file and paste the contents of SKILL.md into your client's custom instructions or system-prompt slot. Bundled reference files can be pasted in too if your client supports longer context.
Power-user install (clone and symlink)
If you'd rather track main directly:
git clone https://github.com/ccromp/marcora-mcp.git
ln -s "$(pwd)/marcora-mcp/skill/marcora-mcp" ~/.claude/skills/marcora-mcp
The unbundled skill source lives under skill/.
Releases
Releases are tagged marcora-vX.Y.Z — see Releases. Each release attaches the bundled skill as marcora-mcp.skill. The skill's own version is the metadata.version field in its SKILL.md, and it moves independently of the release tag.
Available Tools
| Category | Tool | Description |
|---|---|---|
| Account | get_current_user_info |
Get profile, subscription, and usage info |
| Account | get_team_info |
List every team you belong to + each team's members (numeric user_ids for assignment) |
| Account | set_active_team |
Switch your active team (returns previous_team_id to restore) |
| Context & Resources | get_brand_foundation |
Get team's Brand Foundation (company overview, voice, style, examples) |
| Context & Resources | update_brand_foundation |
Overwrite one Brand Foundation element |
| Context & Resources | list_context_collections |
List context collections |
| Context & Resources | create_context_collection |
Create a new context collection |
| Context & Resources | add_context |
Add a context item to your library |
| Context & Resources | update_context |
Update an existing context item |
| Context & Resources | list_context_items |
List context items in your library (optional semantic search) |
| Context & Resources | get_context_item |
Get a context item's full markdown content |
| Context & Resources | get_relevant_context |
Search context library by prompt (with a project_id, also returns the project's brief) |
| Context Intelligence | list_ci_findings |
List findings from automated context-library scans |
| Context Intelligence | get_ci_finding |
Get one finding in full detail by UUID |
| Context Intelligence | update_ci_finding_status |
Acknowledge, dismiss, or resolve a finding |
| Context Intelligence | trigger_health_audit_scan |
Start a library-wide context health audit |
| Content Grounding | check_content_grounding |
Check a document's claims against your context library |
| Content Grounding | get_grounding_result |
Read a grounding scan's result (poll with scan_id) |
| Content Grounding | apply_grounding_fix |
Apply a finding's recommended fix by id |
| Reference | list_content_categories |
List content categories |
| Reference | list_targeting_dimensions |
List targeting dimensions and options |
| Reference | learn_marcora_tools |
Marcora's guide to its own tools, by topic (for assistants without the skill) |
| Blueprints | list_blueprints |
List all blueprints |
| Blueprints | get_blueprint |
Get blueprint details by UUID |
| Blueprints | create_blueprint |
Create a reusable content template |
| Blueprints | create_blueprint_draft |
Create an AI-assisted blueprint draft |
| Blueprints | finalize_blueprint_draft |
Publish a blueprint draft |
| Community Blueprints | list_community_blueprints |
Browse community templates |
| Community Blueprints | get_community_blueprint_details |
Get community blueprint details |
| Community Blueprints | import_community_blueprint |
Import a community blueprint |
| Content | create_content |
Save a new document in the workspace: your own text by default, or written by Marcora (with or without blueprint) |
| Content | get_generation_status |
Check async generation status |
| Content | list_content |
List all content (optional semantic search) |
| Content | get_content |
Get full content by ID |
| Content | update_content |
Update a content document |
| Content | ask_content_assistant |
Run the in-document Content Assistant on a document |
| Sharing & Export | create_external_share |
Create a public share link |
| Sharing & Export | convert_markdown_to_word_doc |
Export markdown as Word doc |
| Projects | list_projects |
List all projects |
| Projects | get_project |
Get project details, including its brief |
| Projects | create_project |
Create a new project |
| Projects | update_project |
Update mutable fields on a project |
| Plans & Playbooks | list_plans |
List content plans (with filters) |
| Plans & Playbooks | get_plan |
Get plan details by UUID |
| Plans & Playbooks | create_plan |
Create a new content plan |
| Plans & Playbooks | update_plan |
Update a plan or transition its stage |
| Plans & Playbooks | produce_plan |
Produce (generate) the content a plan describes |
| Plans & Playbooks | list_playbooks |
List content playbooks |
| Plans & Playbooks | get_playbook |
Get a playbook and its ordered items |
| Plans & Playbooks | create_playbook |
Author a reusable playbook of plan items |
| Plans & Playbooks | create_playbook_from_plans |
Capture existing plans as a playbook |
| Plans & Playbooks | update_playbook |
Rename, re-describe, or restructure a playbook |
| Plans & Playbooks | instantiate_playbook |
Run a playbook into a batch of plans (optionally anchored to a date) |
| Workflows | list_workflows |
List workflows |
| Workflows | get_workflow |
Get a workflow's full definition |
| Workflows | create_workflow |
Create a new workflow template |
| Workflows | update_workflow |
Update, activate, or archive a workflow |
| Workflows | run_workflow |
Run a workflow now |
| Workflows | get_workflow_runs |
Inspect workflow run history |
See docs/tools.md for the complete tool reference.
Documentation
- Overview
- Quickstart
- Authentication
- Tools Reference
- Errors & Troubleshooting
- Security & Privacy
- Changelog
- Support
- Marcora Website Documentation
Security & Privacy
See docs/security.md for details on data handling, permissions, and responsible disclosure.
Support
- Bug reports & feature requests: GitHub Issues
- Website: marcora.ai
License
The documentation, skill, and metadata in this repository are licensed under the MIT License. The Marcora MCP server implementation is proprietary and is not covered by that license or included in this repository.
Marcora MCP questions
How do I add Marcora MCP to Claude Code?
Run claude mcp add --transport http mcp https://mcp.marketcore.ai/ in your terminal. Add --scope user to make it available in every project.
How do I add Marcora MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
What is Marcora?
Marcora is a context layer for go-to-market teams that serves as a single source of truth for positioning, brand voice, and product facts for AI tools.
How do I authenticate with the Marcora MCP server?
You can use OAuth 2.0 for interactive clients or an API Token for non-interactive environments by passing it in an Authorization header.
Can I export my content to other formats?
Yes, the server allows you to export markdown content as a Word document.
Does Marcora support automated workflows?
Yes, it allows you to automate recurring work using reusable, multi-step workflows.