

Agent Tool
Valency Research Paper Library
Details
Give your AI assistant live access to current research. Valency's MCP Bond lets agents search and read public preprints by meaning, within hours of their posting, so answers reflect today's science rather than a model's training cutoff. Find papers on a topic, read the details of a specific preprint, and bring the latest findings into literature reviews, research summaries, and technical decisions. Sign in once with a Valency account and your agents can search current research from any workflow.
Workflows Using This Tool
Workflow
Saves ~4 hr





+1 more tool
Finds recent quantum-chemistry papers with Valency, rebuilds the reported molecule in Chemistry Studio and checks the paper's numbers (geometry, reference state, energies) against exact calculations. It then models the chemical bond as a potential energy curve with exact-gate quantum circuits. For each bond length it runs a classical precision budget (how finely rotation angles must be set to reach chemical accuracy), synthesizes an exact Clifford+T circuit in the Math Engine wherever the angles need finer phases, runs a Qiskit Aer simulation with energies from measurement counts, exports OpenQASM 3 and Qiskit programs, and issues Lean-kernel certificates (qpcert) for every circuit on the curve. The report states exactly what is proven (circuit properties) and what is not (the chemistry). Built for replication studies, method papers and teaching, using molecules such as LiH.
Use Cases
Find recent preprints on a research topic, Summarize the latest findings in a field, Gather sources and citations for a literature review, Check whether new research changes an earlier conclusion, Track new papers on a technology or method, Read a specific preprint before answering a question
Dynamic MCP Setup
Connect once through AgentPMT Dynamic MCP, then use approved tools from the same agent connection.
30 Second Setup
STDIO connector for Claude Code, Codex, Cursor, Zed, and other LLMs that require STDIO or custom connections.
npm install -g @agentpmt/mcp-routeragentpmt-setupHosted Streamable HTTPS
MCP endpoint for browser-based apps like ChatGPT, Claude, Grok, or any time you want a streamable connection with no local install.
https://api.agentpmt.com/mcpConfig Example
Use the hosted endpoint directly in clients that support remote MCP. Store your Bearer token in the client config or secret field.
{
"mcpServers": {
"agentpmt": {
"type": "streamable-http",
"url": "https://api.agentpmt.com/mcp",
"headers": {
"Authorization": "Bearer <AGENTPMT_BEARER_TOKEN>",
"x-instance-metadata": "{\"client\":\"generic-mcp\",\"platform\":\"remote\"}"
}
}
}
}Need client videos, organization controls, audit details, and the full feature overview?
More About Dynamic MCPFrequently Asked Questions
How do I connect this tool to an external agent?
You can install the local MCP server by opening a terminal and running:
Install commands
npm install -g @agentpmt/mcp-router
agentpmt-setupThis will connect you to local agents like Claude Code, Windsurf, Grok Build, Cursor, etc.
Alternatively you can connect to the hosted version with this config block, no installation required:
Hosted MCP config
{
"mcpServers": {
"agentpmt": {
"type": "streamable-http",
"url": "https://api.agentpmt.com/mcp",
"headers": {
"Authorization": "Bearer <AGENTPMT_BEARER_TOKEN>",
"x-instance-metadata": "{\"client\":\"generic-mcp\",\"platform\":\"remote\"}"
}
}
}
}View MCP Connection Instructions for more details.
How does an external agent use this tool?
After the external agent is connected to an Agent Group that can use this tool, paste this prompt into the agent:
Agent prompt
Use the AgentPMT-Tool-Search-and-Execution tool. First call action 'get_instructions' so you know how to use the tool search interface. Then call action 'get_schema' with tool_id 6ada7145e001971070f33005 ("Valency Research Paper Library"). After reading the schema and any returned instructions, tell me what this tool can do, we are going to be using it
The agent should fetch the tool schema first, collect the required parameters for your request, and then call the tool through AgentPMT.
