A side-by-side look at the Fmeca and Line Bot MCP Server MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.
Verdict: choose Fmeca for communication work as a local process; choose Line Bot MCP Server for communication as a local process. You can also run both side by side in one mcpServers block.
session.open, append, state.get.CHANNEL_ACCESS_TOKEN, DESTINATION_USER_ID.postback, message, uri.Rows where the two servers differ are marked.
| Spec | F Fmeca | |
|---|---|---|
| Category | Communication | Communication |
| Quality signal | 56/100 · Good | 84/100 · Excellent |
| Install command | Confirmed | Confirmed |
| Transport | Local subprocess (stdio) | Local subprocess (stdio) |
| Auth | No auth required | API key required |
| Pricing | Free | Free |
| Required env vars | None listed | CHANNEL_ACCESS_TOKENDESTINATION_USER_ID |
| Verified owner | Community listing | Verified |
| GitHub stars | 0 | 789 |
| Directory activity | 0 views 0 installs 0 upvotes | 42 views 0 installs 0 upvotes |
| Tools | 12 | 9 |
| Full listing | View Fmeca | View Line Bot MCP Server |
session.openStart or resume a session; optionally selects the matrix strategy and records analysis metadata (`title`, `level`, `aspect`, `scope_paths`, `parent`), all fixed for the session's life.appendAdd a failure mode (`add_failure_mode`), add a mitigation (`add_mitigation`), or re-score an existing failure mode (`rescore`). `set_mitigation_status` moves a mitigation through planned, implemented, verified or abandoned (verified needs evidence other than a note). `set_failure_mode_disposition`…state.getRead-only projection of the session: every failure mode with its computed criticality, residual, and standing.risk.nextThe highest-criticality unmitigated failure mode — what to address next.readiness.assessThe readiness gate: is every High/Medium residual reduced and every blocker cleared?report.exportThe full FMECA table for the session.scoring.catalogThe fixed observation vocabulary for a strategy — the ids the caller draws from.analyzeStateless one-shot: hand over an entire analysis, get back the entire computed report. No session, no persistence.session.listEvery analysis in the state dir (the project's `.fmeca/` when there is one), with its metadata, standing counts (excluded failure modes are counted separately), `ready`, `ready_verified` and resolution counts. Filters: `level`, `aspect`, `parent`. A log that fails to replay is listed with its error.vetAdvisory: asks Jev (via OpenRouter, needs `OPENROUTER_API_KEY`) whether observations, mitigations, coverage and readiness hold up, and returns probabilities beside the deterministic gate. Never writes or changes a score; without a key it reports `vet_unavailable`.actions.suggestRead-only. Reads a session (or an inline analysis) under a [risk policy](docs/policies.md) and suggests actions: per-failure-mode risk bands, evidence confidence, dispositions, tagged actions and a sign-off verdict. Never changes the analysis or the log.policy.listRead-only. The built-in policy presets and the project's `.fmeca/policies/` files, each with its name, hash and class. A project file that does not load is listed with its `error`.postbackFor sending a postback actionmessageFor sending a text messageuriFor opening a URLdatetimepickerFor opening a date/time pickercameraFor opening the cameracameraRollFor opening the camera rolllocationFor sending the current locationrichmenuswitchFor switching to another rich menuclipboardFor copying text to clipboardPaste 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.
{
"mcpServers": {
"fmeca": {
"command": "npx",
"args": [
"-y",
"@matthew-cochran/fmeca"
]
}
}
}
{
"mcpServers": {
"line-line-bot-mcp-server": {
"command": "npx",
"args": [
"@line/line-bot-mcp-server"
],
"env": {
"CHANNEL_ACCESS_TOKEN": "YOUR_CHANNEL_ACCESS_TOKEN_HERE",
"DESTINATION_USER_ID": "YOUR_DESTINATION_USER_ID_HERE"
}
}
}
}