trust-engine-mcp 0.1.0__tar.gz

trust_engine_mcp-0.1.0/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 Trust Engine AI
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

trust_engine_mcp-0.1.0/PKG-INFO

@@ -0,0 +1,135 @@
+Metadata-Version: 2.4
+Name: trust-engine-mcp
+Version: 0.1.0
+Summary: Free MCP server for AI agents: model retirement dates with sources, public cost-vs-quality benchmark, local usage-cost analysis and a free pilot request.
+Author-email: Trust Engine AI <hello@agenttrustapi.com>
+License-Expression: MIT
+Project-URL: Homepage, https://agenttrustapi.com
+Project-URL: Source, https://github.com/DinevDecor/trust-engine-mcp
+Project-URL: Retirement calendar, https://agenttrustapi.com/retirements/
+Project-URL: For LLM agents, https://agenttrustapi.com/llms.txt
+Keywords: mcp,llm,model-deprecation,model-retirement,llm-cost,ai-agents,evals
+Classifier: Programming Language :: Python :: 3
+Classifier: Operating System :: OS Independent
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: mcp<3.0,>=1.9
+Requires-Dist: httpx<1.0,>=0.27
+Provides-Extra: dev
+Requires-Dist: pytest<9.0,>=8.3; extra == "dev"
+Requires-Dist: ruff>=0.6; extra == "dev"
+Dynamic: license-file
+
+# trust-engine-mcp
+
+Free MCP server from [Trust Engine AI](https://agenttrustapi.com). It answers questions agents otherwise search the web for:
+
+- **Is a model we use being retired, and when?** Verified dates for Anthropic, OpenAI, Google Gemini API and Vertex AI,
+  AWS Bedrock and Mistral. Each date has its official source URL and the date it was checked.
+- **Why do our agents cost so much?** It reads an OpenAI or Anthropic usage/cost export **locally** and shows spend by
+  model, cost drivers and the fixes you can make yourself.
+- **Is a cheaper model good enough?** You get our public benchmark numbers, a savings estimate for the model pairs we
+  measured, and a ready request for a free pilot on your own tasks.
+
+Read-only. No key, no account, no telemetry. The server only sends GET requests to `agenttrustapi.com`.
+
+> **Honesty notes.** The retirement data is copied from vendor pages, so follow `source_url` before you act on a date.
+> The benchmark is one coding agent on 27 public exercises: it compares the models fairly, but it does not predict
+> results on your tasks. Savings estimates exist only for pairs we measured; for any other pair the tool gives no
+> number. Nothing is sent for you: `request_pilot` drafts an e-mail that a person sends.
+
+## Connect with one command
+
+Needs Python 3.10+ and [`uv`](https://docs.astral.sh/uv/).
+
+```bash
+# Claude Code
+claude mcp add --transport stdio trust-engine -- uvx trust-engine-mcp
+
+# Codex CLI
+codex mcp add trust-engine -- uvx trust-engine-mcp
+```
+
+Claude Desktop, Cursor and other stdio clients use this config (`claude_desktop_config.json`, `.cursor/mcp.json`):
+
+```json
+{
+  "mcpServers": {
+    "trust-engine": { "command": "uvx", "args": ["trust-engine-mcp"] }
+  }
+}
+```
+
+Claude Desktop can also install the one-file bundle `trust-engine-mcp-<version>.mcpb` from the GitHub releases.
+Without uv, run `pip install trust-engine-mcp` and use the command `trust-engine-mcp`.
+
+## Try this first
+
+> Use the trust-engine tools. We use claude-sonnet-4-5, gpt-4o and gemini-2.5-flash. Which of them are being
+> retired, on which platform, and by when must we re-test? Cite the sources.
+
+> Here is our usage export (CSV). Why are our agents so expensive? List the quick fixes we can do ourselves this week.
+
+> Is Claude Sonnet good enough instead of Opus for coding work? Show the benchmark numbers and what we would save on
+> a $4,000 monthly bill. Then tell me how to test this on our own tasks.
+
+## Tools
+
+| Tool | Answers |
+|---|---|
+| `check_my_models(models)` | For each model your agent uses: retirement date per platform, days left, the vendor's replacement, the source, and the next step ("re-test before ...") |
+| `model_retirements(provider?, model?, before_date?, include_past?, text_models_only?)` | Upcoming retirements and deprecations, filtered, with sources |
+| `analyze_usage(csv_text? \| rows?)` | Spend by model, top-model share, models on the retirement calendar, cost drivers, next steps. Runs offline; nothing is uploaded |
+| `benchmark_results()` | Public Aider benchmark for Claude Opus, Sonnet and Haiku 5.5: tasks solved, cost per solved task, failed tasks, method and raw data |
+| `estimate_switch_savings(monthly_bill_usd, from_model, to_model)` | Measured cost ratio and the arithmetic, for measured pairs only |
+| `prepare_pilot_tasks(csv_text?, use_case?)` | The pilot task format (CSV template), how to pick 20-30 tasks, how to mask personal data, and an offline check of a draft |
+| `request_pilot(company?, use_case?, models?, task_count?, monthly_bill_usd?, notes?)` | A draft e-mail and `mailto:` link to hello@agenttrustapi.com for a person to send |
+| `pricing()` | Published prices (US$, valid from 12 Nov 2026), incl. the fixed-price 7-day test ($1,390), 24/7 watch and Bulgarian review |
+
+### Usage exports `analyze_usage` reads
+
+Column names are matched loosely; case, spaces and separators are ignored. Only a model column is required.
+
+- model: `model`, `model_name`, `model_id`, `snapshot_id`, `line_item` (e.g. "gpt-4o-2024-08-06, input")
+- cost: `cost`, `cost_usd`, `amount`, `amount_value`, `spend`, `total_cost`
+- requests: `requests`, `num_model_requests`, `n_requests`, `request_count`
+- tokens: `input_tokens`, `prompt_tokens`, `n_context_tokens_total`, `uncached_input_tokens`, `output_tokens`,
+  `completion_tokens`, `cache_read_input_tokens`, `input_cached_tokens`, `cache_creation_input_tokens`
+- reliability: `errors`, `error_count`, `status`, `status_code`, `retries`
+- other: `batch`, `service_tier`, `date`, `start_time`, `bucket_start`
+
+## Data sources
+
+| Data | URL | License |
+|---|---|---|
+| Model retirement calendar | <https://agenttrustapi.com/retirements.json> ([schema](https://agenttrustapi.com/retirements.schema.json), [Atom](https://agenttrustapi.com/retirements.atom), [page](https://agenttrustapi.com/retirements/)) | CC BY 4.0 |
+| Aider model-diet benchmark | <https://agenttrustapi.com/benchmarks/aider-model-diet.json> ([report](https://agenttrustapi.com/reports/model-diet-aider/), [protocol](https://agenttrustapi.com/reports/model-diet-aider/protocol.md), [raw CSV](https://agenttrustapi.com/reports/model-diet-aider/results.csv)) | as on the report |
+| Pilot task template | <https://agenttrustapi.com/pilot/tasks_template.csv> | — |
+
+The server caches each file for 6 hours with a 10-second timeout. The package includes a snapshot of both files. If
+the site is unreachable, the server uses that snapshot and says so in every answer.
+
+## Environment
+
+| Variable | Default | Meaning |
+|---|---|---|
+| `TRUST_ENGINE_OFFLINE` | `0` | `1`: never fetch; use the bundled snapshot only |
+| `TRUST_ENGINE_BASE_URL` | `https://agenttrustapi.com` | data host (for testing against a local copy) |
+
+## Development
+
+```bash
+pip install -e ".[dev]"
+pytest && ruff check .
+```
+
+The tests use fixtures and a fake site. They make no network calls.
+
+## License
+
+Code MIT © 2026 Trust Engine AI. Retirement data CC BY 4.0. Contact: hello@agenttrustapi.com
+
+<!-- Official MCP Registry ownership marker -->
+mcp-name: io.github.DinevDecor/trust-engine-mcp

trust_engine_mcp-0.1.0/README.md

@@ -0,0 +1,111 @@
+# trust-engine-mcp
+
+Free MCP server from [Trust Engine AI](https://agenttrustapi.com). It answers questions agents otherwise search the web for:
+
+- **Is a model we use being retired, and when?** Verified dates for Anthropic, OpenAI, Google Gemini API and Vertex AI,
+  AWS Bedrock and Mistral. Each date has its official source URL and the date it was checked.
+- **Why do our agents cost so much?** It reads an OpenAI or Anthropic usage/cost export **locally** and shows spend by
+  model, cost drivers and the fixes you can make yourself.
+- **Is a cheaper model good enough?** You get our public benchmark numbers, a savings estimate for the model pairs we
+  measured, and a ready request for a free pilot on your own tasks.
+
+Read-only. No key, no account, no telemetry. The server only sends GET requests to `agenttrustapi.com`.
+
+> **Honesty notes.** The retirement data is copied from vendor pages, so follow `source_url` before you act on a date.
+> The benchmark is one coding agent on 27 public exercises: it compares the models fairly, but it does not predict
+> results on your tasks. Savings estimates exist only for pairs we measured; for any other pair the tool gives no
+> number. Nothing is sent for you: `request_pilot` drafts an e-mail that a person sends.
+
+## Connect with one command
+
+Needs Python 3.10+ and [`uv`](https://docs.astral.sh/uv/).
+
+```bash
+# Claude Code
+claude mcp add --transport stdio trust-engine -- uvx trust-engine-mcp
+
+# Codex CLI
+codex mcp add trust-engine -- uvx trust-engine-mcp
+```
+
+Claude Desktop, Cursor and other stdio clients use this config (`claude_desktop_config.json`, `.cursor/mcp.json`):
+
+```json
+{
+  "mcpServers": {
+    "trust-engine": { "command": "uvx", "args": ["trust-engine-mcp"] }
+  }
+}
+```
+
+Claude Desktop can also install the one-file bundle `trust-engine-mcp-<version>.mcpb` from the GitHub releases.
+Without uv, run `pip install trust-engine-mcp` and use the command `trust-engine-mcp`.
+
+## Try this first
+
+> Use the trust-engine tools. We use claude-sonnet-4-5, gpt-4o and gemini-2.5-flash. Which of them are being
+> retired, on which platform, and by when must we re-test? Cite the sources.
+
+> Here is our usage export (CSV). Why are our agents so expensive? List the quick fixes we can do ourselves this week.
+
+> Is Claude Sonnet good enough instead of Opus for coding work? Show the benchmark numbers and what we would save on
+> a $4,000 monthly bill. Then tell me how to test this on our own tasks.
+
+## Tools
+
+| Tool | Answers |
+|---|---|
+| `check_my_models(models)` | For each model your agent uses: retirement date per platform, days left, the vendor's replacement, the source, and the next step ("re-test before ...") |
+| `model_retirements(provider?, model?, before_date?, include_past?, text_models_only?)` | Upcoming retirements and deprecations, filtered, with sources |
+| `analyze_usage(csv_text? \| rows?)` | Spend by model, top-model share, models on the retirement calendar, cost drivers, next steps. Runs offline; nothing is uploaded |
+| `benchmark_results()` | Public Aider benchmark for Claude Opus, Sonnet and Haiku 5.5: tasks solved, cost per solved task, failed tasks, method and raw data |
+| `estimate_switch_savings(monthly_bill_usd, from_model, to_model)` | Measured cost ratio and the arithmetic, for measured pairs only |
+| `prepare_pilot_tasks(csv_text?, use_case?)` | The pilot task format (CSV template), how to pick 20-30 tasks, how to mask personal data, and an offline check of a draft |
+| `request_pilot(company?, use_case?, models?, task_count?, monthly_bill_usd?, notes?)` | A draft e-mail and `mailto:` link to hello@agenttrustapi.com for a person to send |
+| `pricing()` | Published prices (US$, valid from 12 Nov 2026), incl. the fixed-price 7-day test ($1,390), 24/7 watch and Bulgarian review |
+
+### Usage exports `analyze_usage` reads
+
+Column names are matched loosely; case, spaces and separators are ignored. Only a model column is required.
+
+- model: `model`, `model_name`, `model_id`, `snapshot_id`, `line_item` (e.g. "gpt-4o-2024-08-06, input")
+- cost: `cost`, `cost_usd`, `amount`, `amount_value`, `spend`, `total_cost`
+- requests: `requests`, `num_model_requests`, `n_requests`, `request_count`
+- tokens: `input_tokens`, `prompt_tokens`, `n_context_tokens_total`, `uncached_input_tokens`, `output_tokens`,
+  `completion_tokens`, `cache_read_input_tokens`, `input_cached_tokens`, `cache_creation_input_tokens`
+- reliability: `errors`, `error_count`, `status`, `status_code`, `retries`
+- other: `batch`, `service_tier`, `date`, `start_time`, `bucket_start`
+
+## Data sources
+
+| Data | URL | License |
+|---|---|---|
+| Model retirement calendar | <https://agenttrustapi.com/retirements.json> ([schema](https://agenttrustapi.com/retirements.schema.json), [Atom](https://agenttrustapi.com/retirements.atom), [page](https://agenttrustapi.com/retirements/)) | CC BY 4.0 |
+| Aider model-diet benchmark | <https://agenttrustapi.com/benchmarks/aider-model-diet.json> ([report](https://agenttrustapi.com/reports/model-diet-aider/), [protocol](https://agenttrustapi.com/reports/model-diet-aider/protocol.md), [raw CSV](https://agenttrustapi.com/reports/model-diet-aider/results.csv)) | as on the report |
+| Pilot task template | <https://agenttrustapi.com/pilot/tasks_template.csv> | — |
+
+The server caches each file for 6 hours with a 10-second timeout. The package includes a snapshot of both files. If
+the site is unreachable, the server uses that snapshot and says so in every answer.
+
+## Environment
+
+| Variable | Default | Meaning |
+|---|---|---|
+| `TRUST_ENGINE_OFFLINE` | `0` | `1`: never fetch; use the bundled snapshot only |
+| `TRUST_ENGINE_BASE_URL` | `https://agenttrustapi.com` | data host (for testing against a local copy) |
+
+## Development
+
+```bash
+pip install -e ".[dev]"
+pytest && ruff check .
+```
+
+The tests use fixtures and a fake site. They make no network calls.
+
+## License
+
+Code MIT © 2026 Trust Engine AI. Retirement data CC BY 4.0. Contact: hello@agenttrustapi.com
+
+<!-- Official MCP Registry ownership marker -->
+mcp-name: io.github.DinevDecor/trust-engine-mcp

trust_engine_mcp-0.1.0/pyproject.toml

@@ -0,0 +1,51 @@
+[build-system]
+requires = ["setuptools>=68", "wheel"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "trust-engine-mcp"
+version = "0.1.0"
+description = "Free MCP server for AI agents: model retirement dates with sources, public cost-vs-quality benchmark, local usage-cost analysis and a free pilot request."
+readme = "README.md"
+license = "MIT"
+license-files = ["LICENSE"]
+requires-python = ">=3.10"
+authors = [{ name = "Trust Engine AI", email = "hello@agenttrustapi.com" }]
+keywords = ["mcp", "llm", "model-deprecation", "model-retirement", "llm-cost", "ai-agents", "evals"]
+classifiers = [
+    "Programming Language :: Python :: 3",
+    "Operating System :: OS Independent",
+    "Topic :: Scientific/Engineering :: Artificial Intelligence",
+]
+dependencies = [
+    "mcp>=1.9,<3.0",
+    "httpx>=0.27,<1.0",
+]
+
+[project.optional-dependencies]
+dev = ["pytest>=8.3,<9.0", "ruff>=0.6"]
+
+[project.urls]
+Homepage = "https://agenttrustapi.com"
+Source = "https://github.com/DinevDecor/trust-engine-mcp"
+"Retirement calendar" = "https://agenttrustapi.com/retirements/"
+"For LLM agents" = "https://agenttrustapi.com/llms.txt"
+
+[project.scripts]
+trust-engine-mcp = "trust_engine_mcp.server:main"
+
+[tool.setuptools.packages.find]
+where = ["src"]
+
+[tool.setuptools.package-data]
+trust_engine_mcp = ["data/*.json", "data/*.csv"]
+
+[tool.pytest.ini_options]
+testpaths = ["tests"]
+
+[tool.ruff]
+line-length = 120
+target-version = "py310"
+
+[tool.ruff.lint]
+select = ["E", "F", "I", "B", "UP"]

trust_engine_mcp-0.1.0/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+

trust_engine_mcp-0.1.0/src/trust_engine_mcp/__init__.py

@@ -0,0 +1,3 @@
+"""MCP server for Trust Engine AI: model retirement dates, public benchmark numbers and agent cost checks."""
+
+__version__ = "0.1.0"

trust_engine_mcp-0.1.0/src/trust_engine_mcp/__main__.py

@@ -0,0 +1,3 @@
+from trust_engine_mcp.server import main
+
+main()

trust_engine_mcp-0.1.0/src/trust_engine_mcp/data/aider-model-diet.json

@@ -0,0 +1,193 @@
+{
+ "name": "Model diet for a coding agent (Aider): Opus vs Sonnet vs Haiku 5.5",
+ "publisher": {
+  "name": "Trust Engine AI",
+  "url": "https://agenttrustapi.com/",
+  "email": "hello@agenttrustapi.com"
+ },
+ "date": "2026-11-11",
+ "report_url": "https://agenttrustapi.com/reports/model-diet-aider/",
+ "method_url": "https://agenttrustapi.com/reports/model-diet-aider/protocol.md",
+ "raw_data_url": "https://agenttrustapi.com/reports/model-diet-aider/results.csv",
+ "agent": "Aider 0.86.2, default settings per model",
+ "exam": "Aider polyglot benchmark, Python part; hidden tests; one attempt plus one retry with the test output",
+ "exercises_in_analysis": 27,
+ "exercises_planned": 34,
+ "solved_means": "all hidden tests pass after at most one retry (pass@2)",
+ "cost_method": "tokens x list price, read from the agent's own output; not yet reconciled with the invoice",
+ "models": [
+  {
+   "model": "claude-haiku-5-5",
+   "name": "Claude Haiku 5.5",
+   "exercises": 27,
+   "solved_first_try": 15,
+   "solved": 22,
+   "total_cost_usd": 0.2023,
+   "cost_per_exercise_usd": 0.0075,
+   "cost_per_solved_usd": 0.0092,
+   "median_seconds": 30.2,
+   "failed": [
+    "dot-dsl",
+    "forth",
+    "hangman",
+    "paasio",
+    "rest-api"
+   ],
+   "list_price_usd_per_mtok": {
+    "input": 0.1,
+    "output": 0.5
+   }
+  },
+  {
+   "model": "claude-sonnet-5-5",
+   "name": "Claude Sonnet 5.5",
+   "exercises": 27,
+   "solved_first_try": 25,
+   "solved": 26,
+   "total_cost_usd": 3.9499,
+   "cost_per_exercise_usd": 0.1463,
+   "cost_per_solved_usd": 0.1519,
+   "median_seconds": 27.4,
+   "failed": [
+    "paasio"
+   ],
+   "list_price_usd_per_mtok": {
+    "input": 2,
+    "output": 10
+   }
+  },
+  {
+   "model": "claude-opus-5-5",
+   "name": "Claude Opus 5.5",
+   "exercises": 27,
+   "solved_first_try": 26,
+   "solved": 26,
+   "total_cost_usd": 7.7078,
+   "cost_per_exercise_usd": 0.2855,
+   "cost_per_solved_usd": 0.2965,
+   "median_seconds": 33.1,
+   "failed": [
+    "paasio"
+   ],
+   "list_price_usd_per_mtok": {
+    "input": 4,
+    "output": 20
+   }
+  }
+ ],
+ "pairs": [
+  {
+   "from": "claude-haiku-5-5",
+   "to": "claude-sonnet-5-5",
+   "cost_per_solved_ratio": 16.5109,
+   "change_pct": 1551.1,
+   "solved_from": 22,
+   "solved_to": 26,
+   "lost_tasks": [],
+   "gained_tasks": [
+    "dot-dsl",
+    "forth",
+    "hangman",
+    "rest-api"
+   ]
+  },
+  {
+   "from": "claude-haiku-5-5",
+   "to": "claude-opus-5-5",
+   "cost_per_solved_ratio": 32.2283,
+   "change_pct": 3122.8,
+   "solved_from": 22,
+   "solved_to": 26,
+   "lost_tasks": [],
+   "gained_tasks": [
+    "dot-dsl",
+    "forth",
+    "hangman",
+    "rest-api"
+   ]
+  },
+  {
+   "from": "claude-sonnet-5-5",
+   "to": "claude-haiku-5-5",
+   "cost_per_solved_ratio": 0.0606,
+   "change_pct": -93.9,
+   "solved_from": 26,
+   "solved_to": 22,
+   "lost_tasks": [
+    "dot-dsl",
+    "forth",
+    "hangman",
+    "rest-api"
+   ],
+   "gained_tasks": []
+  },
+  {
+   "from": "claude-sonnet-5-5",
+   "to": "claude-opus-5-5",
+   "cost_per_solved_ratio": 1.9519,
+   "change_pct": 95.2,
+   "solved_from": 26,
+   "solved_to": 26,
+   "lost_tasks": [],
+   "gained_tasks": []
+  },
+  {
+   "from": "claude-opus-5-5",
+   "to": "claude-haiku-5-5",
+   "cost_per_solved_ratio": 0.031,
+   "change_pct": -96.9,
+   "solved_from": 26,
+   "solved_to": 22,
+   "lost_tasks": [
+    "dot-dsl",
+    "forth",
+    "hangman",
+    "rest-api"
+   ],
+   "gained_tasks": []
+  },
+  {
+   "from": "claude-opus-5-5",
+   "to": "claude-sonnet-5-5",
+   "cost_per_solved_ratio": 0.5123,
+   "change_pct": -48.8,
+   "solved_from": 26,
+   "solved_to": 26,
+   "lost_tasks": [],
+   "gained_tasks": []
+  }
+ ],
+ "haiku_losses": [
+  {
+   "exercise": "forth",
+   "what": "a small language interpreter: arithmetic and division-by-zero handling",
+   "failing_tests": 11,
+   "tests": 54
+  },
+  {
+   "exercise": "rest-api",
+   "what": "a small REST API: balances between users",
+   "failing_tests": 8,
+   "tests": 9
+  },
+  {
+   "exercise": "dot-dsl",
+   "what": "a graph parser: errors for malformed input",
+   "failing_tests": 3,
+   "tests": 12
+  },
+  {
+   "exercise": "hangman",
+   "what": "a word game: the same correct letter twice counts as a miss",
+   "failing_tests": 1,
+   "tests": 7
+  }
+ ],
+ "limits": [
+  "One agent, one language, 27 of 34 exercises (API credits ran out mid-run; every exercise that finished for all three models is reported).",
+  "Public benchmark: models may have seen it. Comparing models is fair; absolute rates are not a forecast.",
+  "The agent fetched some web pages named in the exercises, which the protocol did not allow.",
+  "Costs are estimates from token counts.",
+  "One public benchmark, not your tasks: a pilot on 20-30 of your own tasks measures what matters to you."
+ ]
+}