Back to search
100
MCP live MCP 2025-11-25 streamable-http

Software Sausage Recipe Finder

io.github.pinkpwningclub/recipes

Find source-linked AI tool recipes and retrieve complete, reproducible run kits.

Watch this dependency Share evidence report
Uptime
100.0%
5 direct probes · 30d
Response
649ms
last probe
Tools
2
callable
Resources
19
readable
Prompts
0
available
Primary URL
https://softwaresausage.com/api/mcp
Score: 100/100
Handshake verified by our own probe.
pass Answers the MCP handshake 50/50
The handshake and the list calls succeeded on the primary URL.
pass Lists tools, resources or prompts 30/30
2 tools, 19 resources, 0 prompts returned.
pass 3 or more catalogue items 10/10
21 items in total; 3 or more earns these points.
pass Describes itself 10/10
80 characters; more than 30 earns these points.

Tools · 2

search_software

Find commercial and open-source software options from the Software Sausage editorial catalog. Results are not paid rankings.

find_agent_recipes

Find read-only, job-focused agent workflows with roles, checks, safety boundaries, source links, and a complete MCP resource URI.

Resources · 19

Write and review a research paper

A compiled paper, source ledger, review findings, and a resolved-claims checklist

sausage://recipes/research-paper
Ship a focused software change

A reviewed diff with test, build, and runtime evidence

sausage://recipes/focused-code-change
Evaluate a coding harness and model combination

A versioned run manifest, raw artifacts, and dimension-by-dimension results

sausage://recipes/evaluate-coding-harness
Triage literature and check citations

A Zotero collection, bibliography export, source ledger, triage shortlist, and citation audit with no unresolved factual claims

sausage://recipes/literature-triage-citation-check
Turn a meeting into an approved decision record

An approved Markdown decision record with timestamped evidence, confirmed owners, due dates, alternatives, and unresolved questions

sausage://recipes/meeting-decision-record
Synthesize customer interviews into a decision brief

A traceable decision brief, theme table, quote ledger, and second-model audit tied back to pseudonymous transcript lines

sausage://recipes/customer-research-synthesis
Summarize sensitive documents without a cloud-model handoff

A locally produced brief with file hashes, model digest, source-linked claim table, extraction exceptions, and human verification status

sausage://recipes/local-private-document-brief
Build an evidence-linked competitor scan

A dated competitor brief, primary-source claim ledger, conflict log, and resolved second-model review

sausage://recipes/evidence-linked-competitor-scan
Turn a CSV or Parquet dataset into a reproducible decision brief

A frozen input manifest, executable SQL, restart-and-run notebook, exported decision brief, and resolved methodology review

sausage://recipes/reproducible-data-analysis
Find and fix an accessibility regression

A reproducible failing case, root-cause fix, passing automated regression check, second-model diff review, and manual-test record

sausage://recipes/accessibility-regression-fix
Audit an MCP server before connecting it

A versioned MCP preflight record with provenance, permission ledger, dependency evidence, negative tests, and an approve, pilot, or reject decision

sausage://recipes/mcp-server-preflight
Turn a software idea into a tested implementation

A linked specification, plan, task ledger, reviewed diff, executable checks, browser evidence, and rollback note

sausage://recipes/spec-to-production-proof
Catch an AI workflow regression before release

A pinned evaluation configuration, frozen cases, comparable run exports, CI result, and reviewed regression decision

sausage://recipes/ai-workflow-regression-test
Compare open-source coding agents on your own repository task

A reproducible fixture, pinned run manifests, raw outputs, verifier results, blind scores, and job-specific selection

sausage://recipes/open-source-coding-agent-benchmark
Choose a document parser without losing decision-critical evidence

A hashed document fixture, two raw extraction sets, fidelity scorecard, source-linked claim ledger, and reviewed parser decision

sausage://recipes/document-parser-fidelity-test
Diagnose and verify a browser performance regression

A reproducible scenario, before-and-after traces, functional checks, bounded root-cause fix, and reviewed performance decision

sausage://recipes/browser-performance-regression
Review an AI-authored code change with three bounded roles

A scope contract, pinned role files, reviewed diff, verifier logs, separate correctness and security findings, runtime proof, and human decision

sausage://recipes/three-agent-code-change-gate
Test whether a multi-agent workflow beats one agent

A frozen fixture, two pinned run manifests, raw artifacts, comparable verifier results, blind scores, and a keep-or-stop decision

sausage://recipes/multi-agent-experiment-gate
Review and land a dependency upgrade safely

A scoped upgrade proposal, dependency and lockfile diff, scan evidence, compatibility patch, passing runtime proof, and rollback record

sausage://recipes/safe-dependency-upgrade

How to use

Claude Desktop or claude.ai: add a custom connector (Customize → Connectors; on Team and Enterprise plans an owner adds it under Organization settings → Connectors) with this server URL: https://softwaresausage.com/api/mcp

Cursor or Cline: add to your MCP config:

{
  "mcpServers": {
    "software_sausage_recipe_finder": {
      "url": "https://softwaresausage.com/api/mcp",
      "transport": "streamable-http"
    }
  }
}