Skip to main content
Hiroshi supports the Model Context Protocol (MCP), which lets you connect external tool servers to the agent. MCP servers run as child processes and communicate with Hiroshi over JSON-RPC 2.0 via stdin/stdout. Any MCP-compatible server can be plugged in — whether it targets a database, a cloud API, a local filesystem, or a custom tool you’ve written yourself.

​
Configuring an MCP server

Add one [mcp_servers.<name>] block per server to your ~/.hiroshi/config.toml. Each block names the executable to run and the arguments to pass it: 
[mcp_servers.my_postgres]
command = "npx"
args = ["-y", "@modelcontextprotocol/server-postgres", "postgresql://localhost/mydb"]

[mcp_servers.filesystem]
command = "npx"
args = ["-y", "@modelcontextprotocol/server-filesystem", "/home/user/projects"]

​
Fields

​
command
string
required
The executable to run. This can be any program that speaks JSON-RPC 2.0 over stdin/stdout — for example npx, python, or uvx.
​
args
array of strings
required
Arguments passed directly to command when the child process is spawned.

​
How MCP tools become available

When the Hiroshi daemon starts, it works through every entry in mcp_servers in sequence:
  1. Spawn — Hiroshi spawns the server process with stdin, stdout, and stderr all piped.
  2. Handshake — Hiroshi sends an initialize request (protocol version 2024-11-05) and waits for acknowledgement.
  3. Discovery — Hiroshi calls tools/list and collects every tool the server advertises.
  4. Skill reflection — Each discovered tool is automatically materialised as a skill folder at ~/.hiroshi/skills/<server>__<tool>/.
  5. Execution — The agent can call any MCP tool just like any other skill. Hiroshi routes the call back to the correct server using the namespaced name.

​
Namespaced tool names

To prevent name collisions between servers, Hiroshi prefixes every MCP tool name with the server key you defined in config.toml: 
<server_name>__<tool_name>
For example, a tool called query on the my_postgres server becomes my_postgres__query. This namespaced form is what you will see in skill folders and in the agent’s tool list.
Servernpm packageWhat it provides
Filesystem@modelcontextprotocol/server-filesystemRead/write access to local directories
PostgreSQL@modelcontextprotocol/server-postgresSQL query and schema inspection
GitHub@modelcontextprotocol/server-githubRepo, PR, and issue management
Brave Search@modelcontextprotocol/server-brave-searchWeb search via the Brave API
Fetch@modelcontextprotocol/server-fetchHTTP fetch and web scraping
SQLite@modelcontextprotocol/server-sqliteLocal SQLite database access
MCP server processes are kept running in the background for the entire lifetime of the Hiroshi daemon. They are not restarted between requests — the same long-lived child process handles all calls to that server.
After adding a server to config.toml, start (or restart) the daemon with hiroshi daemon and then inspect ~/.hiroshi/skills/ to confirm the auto-generated MCP skill folders have appeared. Each folder name follows the <server_name>__<tool_name> pattern.