MCP server
Credence — Epistemic Guard
io.github.Lakshmi-Chakradhar-Vijayarao/credence
Checked 27 Oct 2026, 08:19 UTC · Still published on its registry; checked against OSV.dev; never run by us
Epistemic guard for AI coding: tracks uncertain values and blocks writes until verified.
Runs on your computer
At a glance
- Type
- MCP server
- Publisher
- Not verified
- Status
- Runs on your computer
- Sets up in
- Claude Code, Claude Desktop, Codex, Gemini CLI, Cursor, VS Code
- Last checked
- 27 Oct 2026, 08:19 UTC
Connect it to your agent
Opens the app, which shows the server and asks you to confirm. It then runs the package on your computer with your permissions. For other apps, copy the setup below.
Claude Code
claude mcp add credence -- uvx credence-guard@1.2.5
Claude Desktop
{"mcpServers":{"credence":{"command":"uvx","args":["credence-guard@1.2.5"]}}}
Codex (config.toml)
[mcp_servers.credence] command = "uvx" args = ["credence-guard@1.2.5"]
Gemini CLI
{"mcpServers":{"credence":{"command":"uvx","args":["credence-guard@1.2.5"]}}}
Cursor
{"mcpServers":{"credence":{"command":"uvx","args":["credence-guard@1.2.5"]}}}
VS Code
{"servers":{"credence":{"type":"stdio","command":"uvx","args":["credence-guard@1.2.5"]}}}
Runs on your computer with your permissions: check the package and its source before installing.
Browse
Related MCP servers
- Verdict L402
Ask if an action is safe before your agent runs it: injection, shell, MCP installs. Free samples. - Robinx
Robinhood Chain social signal for trading bots: graded X callers, token verdicts, deployer records. - emem, the verifiable memory protocol for the physical world
Shared, verifiable memory for machines and AI. Encode where data lives; decode with any AI. - Rokha
Search a registry of agent skills and MCP servers, then run them for real. No install, traced. - SAGOT
AI voice agents that place and answer phone calls, with transcripts and outcomes. - DirectMailAmerica
Send one or many U.S. letters, Certified Mail and postcards; manage both email-to-mail services. - ScoreCompute
38 MCP tools: Rust computation, Discovery, composition, counterexample scans and signed checks. - Dominionobservatory Observatory
Runtime behavioral trust scoring for MCP servers. Check reliability before calling unknown tools.
Badge for your README
[](https://aptlynx.net/servers/io.github.Lakshmi-Chakradhar-Vijayarao/credence)
Listing text is written by the maker; AptLynx lists tools and does not vouch for them. Find another tool · Browse by topic · For agents