Ryan/Reactive-Resume
1
0
Fork 0
mirror of https://github.com/AmruthPillai/Reactive-Resume.git synced 2026-07-25 01:15:26 +10:00
Code Issues Packages Projects Releases Wiki Activity

better mcp server

Browse Source
This commit is contained in:
Amruth Pillai
2026-04-09 00:28:31 +02:00
parent 06b9da39ed
commit 1810dc8b07
14 changed files with 1831 additions and 1502 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/guides/using-the-mcp-server.mdx
+42 -22
View File
@@ -207,32 +207,52 @@ If you're running a self-hosted Reactive Resume instance, replace `https://rxres
## Available Tools
The MCP server exposes the following tools:
Tool names use a hierarchical `reactive_resume.*` prefix ([SEP-986](https://github.com/modelcontextprotocol/modelcontextprotocol/issues/986) style) so they stay distinct when multiple MCP servers are enabled in the same client.
| Tool | Description |
| ----------------------- | ---------------------------------------------------------------------------------------------------------------------------------- |
| `list_resumes` | List all resumes with IDs, names, tags, and status. Supports filtering by tags and sorting by last updated, creation date, or name |
| `get_resume` | Get the full data of a specific resume by ID |
| `create_resume` | Create a new, empty resume with a name and slug. Optionally pre-fill with sample data |
| `duplicate_resume` | Create a copy of an existing resume with a new name and slug |
| `patch_resume` | Apply JSON Patch (RFC 6902) operations to modify a resume's data |
| `delete_resume` | Permanently delete a resume and all associated files. **Irreversible** |
| `lock_resume` | Lock a resume to prevent edits, patches, and deletion |
| `unlock_resume` | Unlock a previously locked resume to re-enable editing |
| `export_resume_pdf` | Generate a PDF from the resume and return a download URL |
| `get_resume_screenshot` | Get a visual preview of the resume's first page as a WebP image URL |
| `get_resume_statistics` | Get view and download statistics for a resume |
| Tool | Description |
| --------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------- |
| `reactive_resume.list_resumes` | List all resumes with IDs, names, tags, and status. Supports filtering by tags and sorting by last updated, creation date, or name |
| `reactive_resume.get_resume` | Get the full data of a specific resume by ID |
| `reactive_resume.create_resume` | Create a new, empty resume with a name and slug. Optionally pre-fill with sample data |
| `reactive_resume.duplicate_resume` | Create a copy of an existing resume with a new name and slug |
| `reactive_resume.patch_resume` | Apply JSON Patch (RFC 6902) operations to modify a resume's data |
| `reactive_resume.delete_resume` | Permanently delete a resume and all associated files. **Irreversible** |
| `reactive_resume.lock_resume` | Lock a resume to prevent edits, patches, and deletion |
| `reactive_resume.unlock_resume` | Unlock a previously locked resume to re-enable editing |
| `reactive_resume.export_resume_pdf` | Generate a PDF from the resume and return a download URL |
| `reactive_resume.get_resume_screenshot` | Get a visual preview of the resume's first page as a WebP image URL |
| `reactive_resume.get_resume_statistics` | Get view and download statistics for a resume |
### Breaking change (tool names)
Older clients may refer to unprefixed names (`list_resumes`, `get_resume`, …). Those names are no longer used; update automations and saved prompts to the `reactive_resume.*` names above.
## Available Resources
| Resource | Description |
| ----------------- | --------------------------------------------------------------------------------------------------------------- |
| `resume://{id}` | The full resume data as a readable JSON resource. Lists all resumes and supports reading individual ones by ID |
| `resume://schema` | The ResumeData JSON Schema — reference this to understand valid paths and value types for JSON Patch operations |
Resources follow MCP conventions: **static** items appear in `resources/list`; **parameterized** access is declared in `resources/templates/list` and read via `resources/read` once you know the ID.
| Discovery | What you get |
| ------------------------------------- | --------------------------------------------------------------------------------------------- |
| `resources/list` | Static resources only — currently **`resume://_meta/schema`** (ResumeData JSON Schema) |
| `resources/templates/list` | **`resume://{id}`** — template for reading full resume JSON by ID (not enumerated per resume) |
| `reactive_resume.list_resumes` (tool) | **Primary way to discover resume IDs** — resumes are not listed as separate MCP resources |
| URI | Description |
| ----------------------- | ------------------------------------------------------------------------ |
| `resume://_meta/schema` | ResumeData JSON Schema — use for valid JSON Patch paths and value types |
| `resume://{id}` | Full resume data as JSON — use an ID from `reactive_resume.list_resumes` |
### Breaking change (schema URI)
The schema resource was previously `resume://schema`. It is now **`resume://_meta/schema`**. Update any saved prompts, automations, or client configs that referenced the old URI.
### Static server card (`/.well-known/mcp/server-card.json`)
`GET /.well-known/mcp/server-card.json` returns a JSON document ([SEP-1649](https://github.com/modelcontextprotocol/modelcontextprotocol/issues/1649)) with `serverInfo`, optional authentication metadata, and summaries of tools, resources, resource templates, and prompts. It is generated to match the live MCP server and can be used for discovery when a client cannot run a full capability scan against `/mcp/`.
## Available Prompts
Prompts are pre-built workflows that provide the AI with structured instructions and context. Each prompt embeds the resume data and schema automatically.
Prompts are pre-built workflows that provide the AI with structured instructions and context. Each prompt embeds the resume data and the schema resource (`resume://_meta/schema`) automatically.
| Prompt | Description |
| ---------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------ |
@@ -286,8 +306,8 @@ Once your MCP client is connected, you can use natural language to interact with
- "Tailor my resume for this job description: ..." (uses `tailor_resume`)
<Tip>
The AI will use `get_resume` to inspect your current resume before making changes with `patch_resume`. This ensures
the correct JSON paths are used.
The AI will use `reactive_resume.get_resume` to inspect your current resume before making changes with
`reactive_resume.patch_resume`. This ensures the correct JSON paths are used.
</Tip>
## Troubleshooting
@@ -297,7 +317,7 @@ Once your MCP client is connected, you can use natural language to interact with
| "Unauthorized" with no login prompt | Your client may not support MCP OAuth discovery. Use API key mode (`x-api-key`) |
| OAuth login opens but fails redirect/callback | Confirm your client's MCP OAuth callback settings and retry the connection |
| "API error (401)" | Your API key is invalid or expired. Create a new one in **Settings → API Keys** |
| "API error (404)" | The resume ID doesn't exist. Use `list_resumes` to find valid IDs |
| "API error (404)" | The resume ID doesn't exist. Use `reactive_resume.list_resumes` to find valid IDs |
| "API error (403)" | The resume is locked. Unlock it in the Reactive Resume dashboard |
| Connection refused | Check that the URL is correct and the instance is running |
| "ReferenceError: File is not defined" when using `mcp-remote` | You're running Node.js 18. `mcp-remote` requires **Node.js 20 or later** — upgrade with `nvm use 20` or `nvm alias default 20` |