searchLABSCO SUMMARY
Citations an agent can check rather than invent.
verify_citation is the tool that matters here: an assistant that can confirm a reference exists, then walk outward through the citation graph, stops producing plausible-looking references nobody wrote. The public tools answer without a plan, so the checking half costs nothing to try.
What it is
PapersFlow's hosted research server at https://doxa.papersflow.ai/mcp, over Streamable HTTP. A public read-only tool surface covers search and citations; account and paid workflows sit behind a PapersFlow plan.
What you get
- Literature search and record retrieval — search, search_literature, fetch
- A citation checked against the record it claims — verify_citation
- Related work found from a paper you already have — find_related_papers
- The citation graph around a paper, its immediate neighbours, and an expanded view — get_citation_graph, get_paper_neighbors, expand_citation_graph
- Signed in: evidence summarised across sources — summarize_evidence
- On a plan: deep scans run, polled, snapshotted and read back, plus Python plots — run_deepscan, get_deepscan_status, get_deepscan_live_snapshot, get_deepscan_report, run_python_plot
Requirements
A PapersFlow account. Connect over Streamable HTTP to https://doxa.papersflow.ai/mcp and complete OAuth in the browser, or send a personal access token as an Authorization bearer header. The mcp.public.read scope covers search and citation work; mcp.research.read and mcp.research.run open the plan-only tools. Codex, Claude Code and Gemini CLI are tested against production.
Setup effort
One command plus a key — claude mcp add --transport http papersflow-mcp https://doxa.papersflow.ai/mcp --header "Authorization: Bearer <YOUR_PAPERSFLOW_MCP_TOKEN>"
USE CASES
01
Checking a reference before it goes in a draft
Hand it the citation and get back whether the paper exists as described, rather than trusting a title the model produced from memory.
02
Finding what else was written on a topic
Search the literature, then expand from the most relevant hit into the papers around it instead of running the same query again with different words.
03
Tracing where an idea came from
Pull the citation graph around a paper and expand it a level at a time, so the lineage of a claim is something you can read rather than assume.
14 tools
Listed in project docs. Your client may show a different list.
fetchverify_citationsearch_literaturefind_related_papersget_citation_graphget_paper_neighborsexpand_citation_graphsummarize_evidencerun_deepscanget_deepscan_statusget_deepscan_live_snapshotget_deepscan_reportrun_python_plotBEFORE YOU INSTALL
What to know first
Tools you get
14 tools named in the project's documentation.
Requires
A client that can reach a remote MCP server over HTTP
INSTALLATION
Connect your client
Server setup
claude mcp add
TERMINAL
claude mcp add --transport http papersflow-mcp https://doxa.papersflow.ai/mcp --header "Authorization: Bearer <YOUR_PAPERSFLOW_MCP_TOKEN>"Hosted endpoint
ENDPOINT URL
https://doxa.papersflow.ai/mcpAdd this hosted endpoint to your MCP client, then sign in.
MCP Clients
Cline
CLINE · JSON
{
"mcpServers": {
"papersflow": {
"type": "streamableHttp",
"url": "https://doxa.papersflow.ai/mcp",
"transportType": "streamable-http"
}
}
}Claude Code
CLAUDE CODE · JSON
{
"mcpServers": {
"papersflow-mcp": {
"type": "http",
"url": "https://doxa.papersflow.ai/mcp",
"headers": {
"Authorization": "Bearer <YOUR_PAPERSFLOW_MCP_TOKEN>"
}
}
}
}Gemini CLI
GEMINI CLI · JSON
{
"mcpServers": {
"papersflow-mcp": {
"httpUrl": "https://doxa.papersflow.ai/mcp",
"headers": {
"Authorization": "Bearer <YOUR_PAPERSFLOW_MCP_TOKEN>"
}
}
}
}Codex
CODEX · TERMINAL
export PAPERSFLOW_MCP_TOKEN=<YOUR_PAPERSFLOW_MCP_TOKEN>
codex mcp add papersflow-mcp --url https://doxa.papersflow.ai/mcp --bearer-token-env-var PAPERSFLOW_MCP_TOKEN
