Mcp Client AgentCAUTION
CLI that uses DSPy to interact with MCP servers.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
./clients/mcp_client.py is a CLI that uses DSPy to interact with MCP servers. The goal is to provide a similar experience to Claude Desktop. In particular, the DSPy agent uses the tool definitions defined in the MCP server(s) to autonomously and iteratively use the tools to accomplish the user's request.
The CLI program takes a configuration file in the same format that Claude Desktop uses and loads all of the servers in the config. The tools across all servers are available for the agent to use.
Running the Project
Useful commands for running the project can be found in the Makefile.
Quickstart
- create a
.envfile in the project directory and addOPENAI_API_KEYkey and value. - adjust this path
/Users/shanekercheval/repos/mcp-client-agent/serversin./servers/mcp_fake_server_config.jsonaccordingly make buildmake chat- starts the
chatCLI command using the./servers/mcp_fake_server_config.jsonconfig to start the MCP Server./servers/mcp_fake_server.py - This MCP server contains trivial tools like
count_charactersorcalulator_multiply - this command uses
openai/gpt-4o-minias the model (DSPy model path formatting) and requiresOPENAI_API_KEYto be set in the.envfile
Example using make chat command and mcp_fake_server.py:
Multiply the number of characters in both the following two texts: "Lorem ipsum odor amet, consectetuer adipiscing elit. Nisl ligula molestie nec a sodales morbi vel. Diam interdum metus ante semper, lorem ornare massa. Accumsan dapibus lacus venenatis; elementum varius nascetur nibh sodales ipsum. Suspendisse mauris cubilia sit elit netus mattis. Rhoncus vivamus ridiculus nostra sociosqu bibendum. Eleifend ultricies orci proin maecenas justo felis sagittis. Elit blandit mattis dis consectetur morbi quisque penatibus." and "Lorem ipsum odor amet, consectetuer adipiscing elit. Proin maximus condimentum fusce nam, dictum adipiscing maximus. Lacinia pellentesque
e917b22e88fdOBSERVED · 2026-10-09Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add mcp-client-agent --env OPENAI_API_KEY=${OPENAI_API_KEY} -- uvx mcp-client-agent{
"mcpServers": {
"mcp-client-agent": {
"command": "uvx",
"args": [
"mcp-client-agent"
],
"env": {
"OPENAI_API_KEY": "${OPENAI_API_KEY}"
}
}
}
}Exposed tools (5)
5 read · 0 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
calculator_multiply | read | |
calculator_sum | read | |
count_characters | read | |
count_words | read | |
reverse_text | read |
Trust audit
CAUTIONgrade B · trust 89/100 Install with care. The audit found things worth knowing before you trust its output.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | WARN |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- declared (2 observation(s))
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (3)
--base_url 'http://127.0.0.1:8080' \
--base_url 'http://127.0.0.1:1234/v1' \
.ruff.toml
Gates applied: no_behavioural_pass.
e917b22e88fdfull audit observations/trust-audit/mcp-server/shane-kercheval__mcp-client-agent.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-09 | e917b22e88fd | CAUTION | B | 89 | first audit |
Questions
What is the Mcp Client Agent MCP server?
CLI that uses DSPy to interact with MCP servers.
What tools does Mcp Client Agent expose?
5 in total: 5 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is Mcp Client Agent safe to connect to an agent?
With care. The audit graded it B (89/100) and found 3 things worth knowing before you trust this server, listed below with the exact line each was found on.
What credentials does Mcp Client Agent need?
It reads OPENAI_API_KEY from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does Mcp Client Agent run?
It speaks stdio, so it runs as a local process your client starts. It is published on PyPI as mcp-client-agent.
How current is this page?
The grade is for one exact copy of the source (e917b22e88fd), read on 2026-10-09. The repository is watched and re-audited when it changes.