Research Tracker MCP
by dylanebertco.huggingface.dylanebert/research-tracker-mcp
- Remote endpoint
- 13 tools
Uptime
Checked · every day
100%from 4 days of checks
Up without downtime on 4 of 4 days with data.
- No downtime
- Degraded
- Down over 5 minutes
- No data
- Not checked yet
Response time
Median 1079 ms, slowest 5% 1291 ms for the handshake and the tool list, over 30 days.
How far each check got
- Reached the address 100%
- Completed the handshake 100%
- Listed its tools 100%
13 tools at the last answer.
Every day
| Day | Result | Checks | Median |
|---|---|---|---|
| 3 Nov (today) | No downtime | 1 | 980 ms |
| 2 Nov | No downtime | 1of 1 | 1162 ms |
| 1 Nov | No downtime | 1of 1 | 1147 ms |
| 31 Oct | No downtime | 2 | 998 ms |
A failure counts as down time only when a second check five minutes later fails too. How we check
Connect to the publisher's own endpoint
Paste into Settings › Connectors › Add custom connector:
https://dylanebert-research-tracker-mcp.hf.space/gradio_api/mcp/sse Run in a terminal:
claude mcp add --transport sse research-tracker-mcp https://dylanebert-research-tracker-mcp.hf.space/gradio_api/mcp/sse Add to ~/.cursor/mcp.json:
Add to ~/.config/devin/mcp_config.json:
Add to mcp.json (Program › Install › Edit mcp.json):
Add to ~/.gemini/settings.json:
Add to config.json in oterm's data folder (~/Library/Application Support/oterm on macOS, ~/.local/share/oterm on Linux, %APPDATA%\oterm on Windows):
Add to ~/.config/eca/config.json (global) or .eca/config.json in the project:
{
"mcpServers": {
"research-tracker-mcp": {
"url": "https://dylanebert-research-tracker-mcp.hf.space/gradio_api/mcp/sse"
}
}
} Add to .vscode/mcp.json:
{
"servers": {
"research-tracker-mcp": {
"type": "sse",
"url": "https://dylanebert-research-tracker-mcp.hf.space/gradio_api/mcp/sse"
}
}
} Add to ~/.config/zed/settings.json:
{
"context_servers": {
"research-tracker-mcp": {
"url": "https://dylanebert-research-tracker-mcp.hf.space/gradio_api/mcp/sse"
}
}
} This server's endpoint speaks only SSE, which this client's documentation does not list among its transports; use another client for it.
Add to cline_mcp_settings.json (MCP Servers › Configure › Configure MCP Servers):
Add to anythingllm_mcp_servers.json in the AnythingLLM storage plugins directory:
Add to Augment Settings Panel – MCP section – Import from JSON (VS Code extension):
{
"mcpServers": {
"research-tracker-mcp": {
"type": "sse",
"url": "https://dylanebert-research-tracker-mcp.hf.space/gradio_api/mcp/sse"
}
}
} Add to ~/.continue/config.yaml:
mcpServers:
- name: "research-tracker-mcp"
type: sse
url: "https://dylanebert-research-tracker-mcp.hf.space/gradio_api/mcp/sse" Add to ~/.config/goose/config.yaml:
extensions:
"research-tracker-mcp":
type: streamable_http
name: "research-tracker-mcp"
enabled: true
uri: "https://dylanebert-research-tracker-mcp.hf.space/gradio_api/mcp/sse"
headers: {}
env_keys: []
envs: {}
timeout: 300 This server's endpoint speaks only SSE, which this client's documentation does not list among its transports; use another client for it.
Run in a terminal:
codex mcp add research-tracker-mcp --url https://dylanebert-research-tracker-mcp.hf.space/gradio_api/mcp/sse This server's endpoint speaks only SSE, which this client's documentation does not list among its transports; use another client for it.
Add to ~/.llm/config.json:
Add to resources/assets/config/mcp.json in the installed app:
Add to ~/.boltai/mcp.json:
Add to ~/.bob/settings/mcp.json (global) or .bob/mcp.json (project):
Add to ~/.kiro/settings/mcp.json (user) or .kiro/settings/mcp.json (workspace):
Add to ~/.kiro/settings/mcp.json (user) or .kiro/settings/mcp.json (workspace):
{
"mcpServers": {
"research-tracker-mcp": {
"url": "https://dylanebert-research-tracker-mcp.hf.space/gradio_api/mcp/sse"
}
}
} This server's endpoint speaks only SSE, which this client's documentation does not list among its transports; use another client for it.
Add to ~/.config/agenvoy/mcp.json:
{
"servers": {
"research-tracker-mcp": {
"url": "https://dylanebert-research-tracker-mcp.hf.space/gradio_api/mcp/sse"
}
}
} This server's endpoint speaks only SSE, which this client's documentation does not list among its transports; use another client for it.
Add to ~/.config/amp/settings.json (user) or .amp/settings.json (workspace):
{
"amp.mcpServers": {
"research-tracker-mcp": {
"url": "https://dylanebert-research-tracker-mcp.hf.space/gradio_api/mcp/sse"
}
}
} For agents: the install prompt
Every step above as one Markdown text, for an assistant installing it for you.
# Install the MCP server Research Tracker MCP (`co.huggingface.dylanebert/research-tracker-mcp`)
Its page: https://plug.directory/servers/co.huggingface.dylanebert/research-tracker-mcp
It runs on the publisher's servers; the client connects to its URL.
Use the section for the person's client.
## Claude Desktop
Paste into Settings › Connectors › Add custom connector:
```text
https://dylanebert-research-tracker-mcp.hf.space/gradio_api/mcp/sse
```
## Claude Code
Run in a terminal:
```sh
claude mcp add --transport sse research-tracker-mcp https://dylanebert-research-tracker-mcp.hf.space/gradio_api/mcp/sse
```
## Cursor, Devin Desktop, LM Studio, Gemini CLI, oterm, ECA
Merge into the place for the person's client:
- Cursor: ~/.cursor/mcp.json
- Devin Desktop: ~/.config/devin/mcp_config.json
- LM Studio: mcp.json (Program › Install › Edit mcp.json)
- Gemini CLI: ~/.gemini/settings.json
- oterm: config.json in oterm's data folder (~/Library/Application Support/oterm on macOS, ~/.local/share/oterm on Linux, %APPDATA%\oterm on Windows)
- ECA: ~/.config/eca/config.json (global) or .eca/config.json in the project
```json
{
"mcpServers": {
"research-tracker-mcp": {
"url": "https://dylanebert-research-tracker-mcp.hf.space/gradio_api/mcp/sse"
}
}
}
```
## VS Code
Merge into .vscode/mcp.json:
```json
{
"servers": {
"research-tracker-mcp": {
"type": "sse",
"url": "https://dylanebert-research-tracker-mcp.hf.space/gradio_api/mcp/sse"
}
}
}
```
## Zed
This server's endpoint speaks only SSE, which this client's documentation does not list among its transports; use another client for it.
## Cline, AnythingLLM, Augment Code
Merge into the place for the person's client:
- Cline: cline_mcp_settings.json (MCP Servers › Configure › Configure MCP Servers)
- AnythingLLM: anythingllm_mcp_servers.json in the AnythingLLM storage plugins directory
- Augment Code: Augment Settings Panel – MCP section – Import from JSON (VS Code extension)
```json
{
"mcpServers": {
"research-tracker-mcp": {
"type": "sse",
"url": "https://dylanebert-research-tracker-mcp.hf.space/gradio_api/mcp/sse"
}
}
}
```
## Continue
Merge into ~/.continue/config.yaml:
```yaml
mcpServers:
- name: "research-tracker-mcp"
type: sse
url: "https://dylanebert-research-tracker-mcp.hf.space/gradio_api/mcp/sse"
```
## Goose
This server's endpoint speaks only SSE, which this client's documentation does not list among its transports; use another client for it.
## Codex
This server's endpoint speaks only SSE, which this client's documentation does not list among its transports; use another client for it.
## mcp-client-cli, TUUI, BoltAI, Bob Shell, Kiro, Kiro CLI
This server's endpoint speaks only SSE, which this client's documentation does not list among its transports; use another client for it.
## Agenvoy
This server's endpoint speaks only SSE, which this client's documentation does not list among its transports; use another client for it.
## Amp
Merge into ~/.config/amp/settings.json (user) or .amp/settings.json (workspace):
```json
{
"amp.mcpServers": {
"research-tracker-mcp": {
"url": "https://dylanebert-research-tracker-mcp.hf.space/gradio_api/mcp/sse"
}
}
}
```
Then restart the client, or reload its MCP servers, and ask it to list the server's tools to confirm it started.
Tools 13
research_tracker_mcp_classify_research_urlClassify the type of research-related URL or input. This tool identifies resource types based on URL patterns: - Paper: arXiv, HuggingFace papers, PDF files - Code: GitHub repositories - Model: HuggingFace model pages - Dataset: HuggingFace dataset pages - Space: HuggingFace space/demo pages - Project: GitHub.io pages - Unknown: Unrecognized patterns. Returns: The field type: "Paper", "Code", "Space", "Model", "Dataset", "Project", or "Unknown"research_tracker_mcp_find_research_relationshipsFind ALL related research resources across platforms for comprehensive analysis. Uses a multi-round discovery approach to build a complete resource graph. This is a comprehensive tool that combines all individual inference tools to provide a complete picture of a research project's ecosystem. It discovers: - Paper URLs (arXiv, HuggingFace) - Code repositories (GitHub) - Models, datasets, and demo spaces (HuggingFace) - Author information and publication dates - License information. Returns: Dictionary containing all discovered related resourcesresearch_tracker_mcp_infer_authorsInfer authors from research paper or project information. This tool extracts author names from: - arXiv papers (via API) - HuggingFace paper pages (via scraping) - GitHub repositories (via API when GITHUB_AUTH is set). Returns: A list of author names as strings, or empty list if no authors found., ["Alec Radford", "Jong Wook Kim", "Chris Hallacy"], , If input_data is invalid or malformed, If external API calls fail after retriesresearch_tracker_mcp_infer_code_repositoryInfer the code repository URL from research-related inputs. This tool discovers code repositories by: - Scraping HuggingFace paper pages for GitHub links - Searching GitHub for repositories by paper title - Extracting repository links from project pages. Returns: The code repository URL (typically GitHub), or empty string if not found, "https://github.com/google-research/vision_transformer"research_tracker_mcp_infer_datasetInfer associated HuggingFace dataset from research paper or project information. Returns: HuggingFace dataset URL, or empty string if no dataset foundresearch_tracker_mcp_infer_licenseInfer license information from research repository or project. Returns: License name/type, or empty string if no license foundresearch_tracker_mcp_infer_modelInfer associated HuggingFace model from research paper or project information. Returns: HuggingFace model URL, or empty string if no model foundresearch_tracker_mcp_infer_paper_urlInfer the paper URL from various research-related inputs. This tool finds paper URLs by: - Validating existing paper URLs - Searching GitHub repositories for paper links - Converting between arXiv and HuggingFace paper formats - Searching by paper title when provided. Returns: The paper URL (typically arXiv or Hugging Face papers), or empty string if not found, "https://huggingface.co/papers/2103.00020"research_tracker_mcp_infer_publication_dateInfer publication date from research paper or project information. Returns: Publication date as string (YYYY-MM-DD format), or empty string if not foundresearch_tracker_mcp_infer_research_nameInfer the research paper or project name from various inputs. Returns: The research name/title, or empty string if not foundresearch_tracker_mcp_infer_spaceInfer associated HuggingFace space from research paper or project information. Returns: HuggingFace space URL, or empty string if no space foundresearch_tracker_mcp_process_research_relationshipsProcess research input and return formatted results
From Hugging Face Spaces. Report a problem