You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: README.md
+13-10Lines changed: 13 additions & 10 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -22,7 +22,7 @@ We're developing a Kubernetes operator, guided by our internal roadmap, to exten
22
22
23
23
## The Problem
24
24
25
-
ML teams build agents that work perfectly locally. Operations teams get handed Python scripts and told "make this production-ready across dev/UAT/prod."
25
+
ML teams build agents that work perfectly locally. Operations teams often get handed Python scripts with little context and told "make this production-ready across dev/UAT/prod."
26
26
The gap between local development and enterprise deployment kills AI initiatives.
27
27
28
28
`mcpd` solves this with declarative configuration, secure secrets management, and seamless environment promotion - all while keeping the developer experience simple.
@@ -31,19 +31,19 @@ The gap between local development and enterprise deployment kills AI initiatives
31
31
## Why `mcpd`?
32
32
33
33
**Zero-Config Tool Setup**
34
-
No cloning repos or installing language-specific dependencies. `mcpd add` and `mcpd daemon` handle everything.
34
+
No need to clone multiple repos or install language-specific dependencies. `mcpd add` and `mcpd daemon` handle everything.
35
35
36
36
**Language-Agnostic Tooling**
37
-
Use MCP servers in Docker containers or written in Python, JavaScript, TypeScript via a unified HTTP API.
37
+
Use MCP servers in Docker containers or written in Python, JavaScript, or TypeScript via a unified HTTP API.
38
38
39
39
**Declarative Configuration**
40
40
Version-controlled `.mcpd.toml` files define your agent infrastructure. Reproducible, auditable, CI-friendly.
41
41
42
42
**Enterprise-Ready Secrets**
43
-
Separate project configuration from runtime variables, and export sanitized secrets templates. Never commit secrets to Git again.
43
+
Separate project configuration from runtime variables, and export sanitized secrets templates. No need to commit secrets to Git ever again.
44
44
45
45
**Seamless Local-to-Prod**
46
-
Same configuration works in development, CI, and cloud environments without modification.
46
+
Same configuration works in development, CI, and cloud environments without modification or risky hand-offs.
47
47
48
48
49
49
## Built for Dev & Production
@@ -68,10 +68,13 @@ Same configuration works in development, CI, and cloud environments without modi
|`Docker`| For running MCP servers as Docker containers |[https://www.docker.com/products/docker-desktop/](https://www.docker.com/products/docker-desktop/)|
8
-
|`Go >= 1.25.0`| Required for building `mcpd` and running tests |[https://go.dev/doc/install](https://go.dev/doc/install)|
8
+
|`Go >= 1.25.1`| Required for building `mcpd` and running tests |[https://go.dev/doc/install](https://go.dev/doc/install)|
9
9
|`uv`| For running `uvx` Python packages in `mcpd`, and local docs |[https://docs.astral.sh/uv/getting-started/installation/](https://docs.astral.sh/uv/getting-started/installation/)|
10
10
|`npx`| For running JavaScript/TypeScript packages in `mcpd`|[https://docs.npmjs.com/downloading-and-installing-node-js-and-npm](https://docs.npmjs.com/downloading-and-installing-node-js-and-npm)|
0 commit comments