Agentcast vs Mdma
A side-by-side look at the Agentcast and Mdma MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.
Verdict: choose Agentcast for conversational ai work as a local process; choose Mdma for conversational ai as a local process. You can also run both side by side in one mcpServers block.
Which MCP server should you choose?
Choose Agentcast when
- You need dedicated capabilities in the Conversational AI domain.
- You prefer a local stdio subprocess transport.
- You want tools like
extract_json, validate_response, build_retry_prompt.
Choose Mdma when
- You need dedicated capabilities in the Conversational AI domain.
- You prefer a local stdio subprocess transport.
- You want tools like
get-spec, get-prompt, list-prompt-variants.
Feature & specification comparison
Rows where the two servers differ are marked.
| Spec | ||
|---|---|---|
| Category | Conversational AI | Conversational AI |
| Quality signal | 57/100 · Good | 59/100 · Good |
| Install command | Confirmed | Confirmed |
| Transport | Local subprocess (stdio) | Local subprocess (stdio) |
| Auth | Not declared | Not declared |
| Pricing | Not declared | Not declared |
| Required env vars | None listed | None listed |
| Verified owner | Community listing | Community listing |
| GitHub stars | 1 | 71 |
| Directory activity | 1 views 0 installs 0 upvotes | 0 views 0 installs 0 upvotes |
| Tools | 3 | 8 |
| Full listing | View Agentcast | View Mdma |
Tools & capabilities
Agentcast tools 3
extract_jsonPull a JSON value out of messy LLM output. Tries the whole text, then a fenced ```json``` block, then the largest balanced {...}/[...] substring. Returns the parsed value plus which strategy succeeded.validate_responseValidate a parsed JSON value against an agentcast shape spec. Spec maps field name to type: 'string', 'number', 'boolean', 'array', 'object'. Suffix with '?' for optional. Returns valid=true on success, or valid=false with a human-readable error string suitable for retry feedback.build_retry_promptGiven an attempt history, produce the retry feedback message agentcast would append to the conversation when the model returned the wrong shape. Codifies the "validation error as feedback" pattern for non-Node MCP clients.
Mdma tools 8
get-specReturns the full MDMA specification: component types, JSON schemas, binding syntax, external data sources (`{ source, params }` refs and the `rows` / `series` / `options` kinds), and authoring rulesget-promptReturns a named prompt (`mdma-author`, `mdma-reviewer`, or `mdma-fixer`). For `mdma-author`, accepts an optional `variantId` (e.g. `google/gemini-2.5-pro`) to return the model-optimised variantlist-prompt-variantsReturns all available `MDMA_AUTHOR` prompt variants (id, label, description) — use the id with `get-prompt` to fetch the model-optimised promptbuild-system-promptGenerates a custom MDMA prompt from structured input (domain, components, fields, steps, business rules). Pass `dataSources` (an external data-source catalog of `rows` / `series` / `options` entries) to get the full system prompt with the catalog and the rule to reference data via `{ source, params…validate-promptValidates a custom prompt against MDMA conventions — returns warnings, suggestions, and constraint referencelist-packagesReturns all MDMA packages with purpose, install command, and usage examplelist-docsReturns the catalog of MDMA documentation files (path, title, description) available for fetching from the public GitHub repoget-docFetches the latest version of an MDMA documentation file from `raw.githubusercontent.com/MobileReality/mdma`. Supports optional `ref` (branch/tag/SHA, defaults to `main`)
Ready-to-paste client configs
Paste either block (or both) into your client config, e.g. claude_desktop_config.json or ~/.cursor/mcp.json. We only show a config when the install command is confirmed.
Agentcast
{
"mcpServers": {
"agentcast": {
"command": "npx",
"args": [
"-y",
"@mukundakatta/agentcast-mcp"
]
}
}
}
Mdma
{
"mcpServers": {
"mdma": {
"command": "npx",
"args": [
"-y",
"@mobile-reality/mdma-cli"
]
}
}
}
Frequently asked questions
Agentcast is categorized under Conversational AI and uses a local stdio subprocess. Mdma belongs to Conversational AI and uses a local stdio subprocess. Pick Agentcast for conversational ai work and Mdma for conversational ai.
Copy the mcpServers block from the config section on this page into your client's config (for example claude_desktop_config.json or ~/.cursor/mcp.json), then fully restart the client.
Agentcast has no declared pricing — check the project's own site. Mdma has no declared pricing — check the project's own site. If a server needs environment variables such as API keys, define them under the env key in your client's MCP config.
Yes. MCP clients support multiple servers: add agentcast and mdma as separate keys in the same mcpServers object, and your assistant will call tools from either one.
On AllMCPs, Agentcast has a quality signal of 57/100 (Good) with 1 views, 0 installs and 1 GitHub stars. Mdma has 59/100 (Good) with 0 views, 0 installs and 71 GitHub stars.