Was this page helpful?
Add this under mcp_servers in your Hermes config file (~/.hermes/config.yaml). Zephex is a remote hosted MCP server at https://zephex.dev/mcp — url plus Bearer headers, no npx block. Internet required. See Hermes Agent docs for how Hermes handles MCP on their side.
HTTP and stdio setups both need a key from your Zephex dashboard. OAuth-only flows (ChatGPT, Claude.ai web) sign you in in the browser instead — skip this section for those.
Hermes reads one global config file. Project-specific repos are selected in chat via paths, not separate YAML files.
Replace mcp_sk_your_key_here with your key from Dashboard → API Keys. Copy the full key once at creation — paste into Authorization: Bearer … for HTTP configs, or into ZEPHEX_API_KEY for stdio/npx configs.
HTTP MCP with API key auth. Other servers can stay under mcp_servers — indent zephex at the same level as them.
mcp_servers: zephex: url: "https://zephex.dev/mcp" headers: Authorization: "Bearer mcp_sk_your_key_here"Tip
YAML is sensitive to indentation — zephex must line up under mcp_servers with two spaces per level.
After saving your config, confirm Zephex is connected before you rely on it in real work.
You do not call tools yourself — ask your agent in plain language. Try these once Zephex is connected:
“Hermes agent: get_project_context on github:anthropics/claude-code — scripts and deps.”
YAML mcp_servers remote session — no Hermes-local Zephex binary.
“find_code tool dispatch table in our agent repo.”
Locate extension points before patching Hermes workflows.
“check_package on PyPI package proposed in a skill file.”
Supply-chain gate for autonomous Hermes runs.
“keep_thinking across a multi-step refactor — record what we already ruled out.”
Persistent reasoning for long Hermes jobs.
“explain_architecture for our plugin host and MCP client boundary.”
Clear diagram for contributors.
“audit_package bump for httpx in our pyproject.toml.”
Version delta risks before poetry lock refresh.
You do not pick tools from a menu — ask your agent in normal sentences. Half of the tools only need a package name or URL; the other half need to know which codebase you mean (your Mac/Windows project folder or a GitHub repo).
These situations usually mean the setup cannot work until you fix the underlying issue:
YAML parse error on launch
Use spaces not tabs. Quote url and Authorization. Validate with a YAML linter.
stdio config still present
Delete command/args/env blocks for zephex — use only url and headers.
401 from Zephex
Authorization value must be Bearer mcp_sk_... inside double quotes.
Works on Mac path, not Windows
Use C:\Users\you\project or github: URL — Hermes does not translate ~ across platforms in tool args.
explain_architecture empty
Pass github:owner/repo or absolute path to repo root in the same request.
Hermes mcp_servers YAML connects to the same ten-tool hosted endpoint:
get_project_context
Reads your project structure, dependencies, scripts, env vars, and framework markers in one call. Replaces manually opening package.json, tsconfig, and multiple config files at the start of every session.
read_code
AST-based code extraction: pass a symbol name and get the implementation without reading entire files. Supports symbol lookup, batched file reads, and structural outlines for large files.
find_code
Ranked search across the repo for definitions, usages, and patterns. Faster than blind grep when the agent does not know where a symbol lives.
check_package
Live registry lookup for npm, PyPI, Cargo, and Go modules. Surfaces typosquat risk, maintainer changes, and suspicious version jumps before you run install.
audit_package
Deep package intelligence: CVEs with severity, breaking changes between versions, migration notes, and peer-dependency conflicts.
explain_architecture
Generates Mermaid diagrams for auth flows, service boundaries, and module dependencies so the agent reasons about structure instead of guessing.
scope_task
Turns a task description into the smallest file set to read or edit, with risk ratings and caller impact notes.
audit_headers
Grades a deployed URL for CSP, HSTS, TLS, cookies, and redirects. Returns fix snippets for common hosts (Vercel, Cloudflare, Nginx).
keep_thinking
Structured multi-step debugging: tracks hypotheses and conclusions so long investigations do not loop.
Zephex_dev_info
Expert patterns for authentication, databases, frontend frameworks, deployment, and mobile stacks when the agent needs vetted guidance.