Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@delivery-intelligence-mcp what's the programme health and key risks?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
A governed AI/MCP delivery-intelligence showcase over a fully synthetic enterprise programme.
It helps a delivery lead answer: what changed, what is blocked, which dependency matters next, what a change request will affect, and which claims are supported by evidence. The core value works without an API key.
Open the generated workbench: workbench/index.html
Inspect the architecture: docs/architecture.md
Review the engine/tool boundary: delivery_intelligence/engine.py and delivery_intelligence/mcp_server.py
Check the evaluation harness: docs/evaluation.md
Run the project:
python -m pip install -e .
python -m delivery_intelligence build
python -m delivery_intelligence validate
python -m unittest discover -s testsRelated MCP server: OntoRamp Transformation Radar
Capability | Public evidence |
AI/MCP tool design | Eight focused MCP tools over a coherent programme model, with structured outputs and validated arguments. |
Delivery/programme thinking | Milestones, RAID, decisions, change requests, readiness gates, dependencies and steering context pack. |
Hallucination controls | Unsupported claims return |
Evidence traceability | Outputs separate source facts, deterministic derivations and recommendations with evidence references. |
Evaluation discipline | Deterministic checks cover tool contracts, evidence coverage, refusal behavior, recursive change impact, snapshot deltas and repeatability. |
Cost/latency awareness | Tool outputs include latency and estimated-cost telemetry; deterministic core has zero model cost. |
flowchart LR
A[Synthetic programme fixture] --> B[Deterministic delivery engine]
B --> C[Evidence ledger]
B --> D[Tool registry]
D --> E[Optional MCP server]
D --> F[Evaluation harness]
D --> G[Generated workbench]
H[Future data adapter] -. documented boundary .-> A
I[Optional narrative adapter] -. recommendations only .-> DThe public showcase stands alone. It does not import another portfolio repo and does not expose private operational, job-search, email, salary, eligibility, credential or account data.
Tool | Purpose |
| Explainable health score with formula, limitations and evidence. |
| Deterministic RAID prioritisation by severity, probability, impact and overdue status. |
| Downstream dependency traversal from a milestone. |
| Schedule, cost, scope and readiness impact for a change request. |
| Snapshot delta across health, risks, decisions, milestones, readiness gates, change requests and evidence keys. |
| Blocked decisions, blockers and missing evidence. |
| Board-ready context pack with facts, derivations and recommendations separated. |
| Evidence lookup or refusal when support is insufficient. |
Layer | Meaning | Example |
Source facts | Synthetic fixture records: milestones, RAID, dependencies, decisions, gates and snapshots. | Payment freeze forecast moved to day 92. |
Deterministic derivations | Python-calculated scores, risk ranks, impact paths and evidence coverage. | Payment freeze slippage propagates to pilot launch. |
Recommendations | Policy suggestions generated from traceable facts and derivations. | Split or defer a change request unless sponsor accepts schedule impact. |
Optional AI narrative | Future adapter boundary only; not required for tests or demo. | A model may rewrite a steering summary, but cannot create unsupported facts. |
The core package has no runtime dependencies. To run the real MCP server using the official Python SDK:
python -m pip install -e ".[mcp]"
delivery-intelligence-mcpThe MCP extra is optional because the deterministic engine, workbench and evaluation harness should remain reviewable without service credentials or model access.
The repo includes a root index.html entrypoint for GitHub Pages. Pages is not currently enabled on the public repository. To make the live route work, enable GitHub Pages from main / root in repository settings; the expected URL will be https://mypoorbrain.github.io/delivery-intelligence-mcp-workbench/.
Run:
python -m delivery_intelligence evalThe harness checks:
tool-call contract validity;
evidence coverage for health and steering outputs;
unsupported-claim refusal;
change/dependency impact correctness against the known fixture;
recursive change-impact propagation;
snapshot delta detection;
repeatability across deterministic runs;
latency and estimated-cost telemetry presence.
Synthetic programme only.
No external actions.
No broad file-system, network or shell tools.
No vector database or orchestration framework.
No API key required.
No private programme, job-search, resume, recruiter, account, salary, legal, eligibility or credential data.
Future adapters must preserve the same evidence boundary.
delivery_intelligence/
fixtures.py synthetic programme records
engine.py health, risk, dependency, change and evidence reasoning
tools.py validated tool registry and telemetry wrapper
mcp_server.py optional real MCP server using the Python SDK
evaluation.py deterministic evaluation harness
workbench.py generated HTML/SVG workbench artifacts
tests/ engine, tool, evaluation and visual-output checks
docs/ architecture, tool, evaluation and portfolio notes
workbench/ generated self-contained workbenchMIT.
This server cannot be deployed
Read-only AI coding tools for change verification, release readiness, capacity, and guidance.
Generate answers & visualizations from your engineering data to track software development health.
Durable, shareable and governed project memory with smart triage and explicit project composition.
Multi-expert decision intelligence with transparent synthesis and auditable workflows.
