forgejo-projects-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| FORGEJO_URL | Yes | The base URL of the Forgejo instance (always required). | |
| FORGEJO_MCP_RPS | No | Request rate limit in requests per second (default 5). | |
| FORGEJO_PASSWORD | No | Forgejo password. Required when a fresh login is needed (e.g., no cached session). | |
| FORGEJO_USERNAME | No | Forgejo username. Required when a fresh login is needed (e.g., no cached session). | |
| FORGEJO_MCP_LOG_LEVEL | No | Logging level for the MCP server. | |
| FORGEJO_MCP_MAX_CONCURRENCY | No | Maximum concurrency for bulk reads (default 8). |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| forgejo_statusA | Report whether the MCP is authenticated to the Forgejo instance. Reads credentials from FORGEJO_URL / FORGEJO_USERNAME / FORGEJO_PASSWORD and authenticates if needed, persisting the session under the OS config dir (e.g. ~/.config/forgejo_projects_mcp/). |
| authenticateA | Authenticate to Forgejo and cache the session. Args: force: If true, ignore any cached session and log in fresh. |
| list_repositoriesA | List repositories the current user can access (for choosing where to manage projects). Args: query: Optional name filter. limit: Max results (default 50). page: Page number (default 1). |
| list_projectsA | List projects (kanban boards) in a repository. Args: owner: Repository owner (user or org). repo: Repository name. state: 'open', 'closed', or 'all'. |
| create_projectA | Create a new project/kanban board in a repository. Args: owner: Repository owner. repo: Repository name. title: Project title. description: Optional description. card_type: 'text' or 'images_and_text'. |
| get_projectB | Get a project board: its columns and the cards (issues) in each. Returns column ids/titles and, per card, the issue id, number and title. |
| update_projectC | Update a project's title, description and/or card type. |
| close_projectC | Close (archive) a project. |
| reopen_projectC | Reopen a closed project. |
| delete_projectA | Permanently delete a project. This does not delete its issues. |
| create_columnC | Add a column to a project board. Args: color: Optional hex color, e.g. '#e01e5a'. |
| edit_columnB | Edit a column's title and/or color. |
| delete_columnA | Delete a column. Its cards return to the default/uncategorized column. |
| set_default_columnA | Set a column as the project's default (where new cards land). |
| create_issueA | Create an issue, optionally placing it directly on a project board. Args: project_id: If given, the issue is added to that project as a card. milestone_id: Optional milestone to attach. label_ids / assignee_ids: Optional numeric ids. |
| add_issues_to_projectB | Add existing issues (by their repo issue numbers) to a project as cards. |
| remove_issues_from_projectB | Remove issues (by number) from any project board. The issues themselves survive. |
| move_cardC | Move one or more cards (issues, by number) into a column, in the given order. |
| delete_issueC | Permanently delete an issue by number. |
| bulk_move_cardsA | Move many cards at once, each to its own column. Args: moves: list of {"issue_number": N, "column_id": C}. Cards going to the same column are placed in the order listed. Runs concurrently. |
| bulk_read_issuesA | Read a summary (number, title, state, milestone) of many issues at once. Lightweight — bodies and comments are omitted. Use read_card for full content. Args: state: 'open', 'closed', or 'all' (default) — filters the returned issues. Returns |
| read_cardA | Full content of one card/issue: title, state, body, milestone, and all comments. ⚠️ Network- and token-expensive. Avoid unless asked or necessary. |
| read_columnA | Full content of every card in a column. Args: state: 'open', 'closed', or 'all' (default). milestone: optional milestone id to restrict to. limit: max cards to read this call (None = no limit); offset to page. ⚠️ Network- and token-expensive. Avoid unless asked or necessary; use limit/offset to cap cost. |
| read_milestoneA | Full content of every issue attached to a milestone. Args: state: 'open', 'closed', or 'all' (default). project: optional project id to restrict to. limit: max issues to read this call (None = no limit); offset to page. ⚠️ Network- and token-expensive. Avoid unless asked or necessary; use limit/offset to cap cost. |
| read_projectA | Full content of an entire board: every column and every card's content. Args: state: 'open', 'closed', or 'all' (default). milestone: optional milestone id to restrict to. limit: max cards to read this call (None = no limit); offset to page. ⚠️ Network- and token-expensive. Avoid unless asked or necessary; use limit/offset to cap cost. |
| list_milestonesA | List milestones in a repository ('open', 'closed', or 'all'). |
| create_milestoneC | Create a milestone. Args: deadline: Optional due date, 'YYYY-MM-DD'. |
| edit_milestoneA | Edit a milestone's title, description and/or deadline ('YYYY-MM-DD'). |
| close_milestoneC | Close a milestone. |
| reopen_milestoneC | Reopen a closed milestone. |
| delete_milestoneC | Delete a milestone. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/UnwantedForeignCloudProvider/ForgejoProjectsMCP'
If you have feedback or need assistance with the MCP directory API, please join our Discord server