MCP servers that ship as code — a repository or a package you install and run locally (usually over stdio). They have no hosted endpoint, so we cannot probe or grade them: instead each one shows its repository, install command, license, stars and when it was last updated.
Collected from GitHub repositories and npm, PyPI, Cargo, Go, Maven, NuGet and RubyGems packages tagged as MCP servers, the official MCP Registry, Docker's MCP catalog, ModelScope, Baidu MCP World, Cline and other public directories; one entry per repository. A server that also offers a hosted endpoint is listed under Remote instead. These entries are not counted in our reachability, verification or readiness statistics.
-
Domain-specific synthetic data generation MCP server for healthcare and finance compliance
pypi MIT -
Databricks MCP Server for Synthetic Data Generation with dbldatagen
pypi MIT -
Schema-aware synthetic test data with deterministic replay, relational integrity, business rules, and MCP tools.
MIT -
ai-data-platformgithub.com/yogi776/data-generation-sdkupdated this year
AI Data Platform: metadata catalog, profiling, synthetic data generation, semantic models, NL-to-SQL, and MCP server — local-first.
pypi Apache-2.0 -
seedfakergithub.com/opendsr-std/seedfakerupdated this year
Deterministic synthetic data generator — realistic, correlated, noisy test records across 68 locales (CLI + Python + Node.js + Go + PHP + Ruby + MCP)
cargo MIT -
Seed-to-scale LLM synthetic data engine with auto-detected templates, schema validation & quality-diversity optimization. CLI + MCP ready.
MIT ★ 1 -
Synthetic-data career workflow MCP sample for resume tailoring, opportunity tracking, and interview prep
MIT -
@mimicai/coregithub.com/mimicailab/mimicupdated this year
Core engine for Mimic — persona-driven synthetic data generation, schema parsing, database seeding, and MCP server
npm Apache-2.0 -
clutter-mcpgithub.com/michaelhologram/clutter-mcpupdated this year
Generate synthetic companies, documents & data via the Clutter API (e.g. to fill SharePoint or CRM). MCP server.
npm MIT -
An AI-native 3D renderer + lightweight physics simulator, driven by coding agents (MCP), for robotics and synthetic-data generation.
Apache-2.0 ★ 3 -
Plain-English request to Grafana dashboard through the Grafana MCP server, on synthetic data, all on one laptop
MIT -
Illustrative sample on synthetic data (no client relationship): MCP server with per-tool scopes, tenant isolation, human approval and a hash-chained audit log.
MIT -
A realistic fictional small business for testing AI agents: synthetic data generator, mock CRM/inbox/calendar/invoicing MCP servers, and verified workflow tasks.
npm Apache-2.0 -
Model-driven synthetic test data for CI/CD and analytics - deterministic, privacy-preserving, and domain-aware. Includes Python APIs, XML pipelines, and MCP/IDE integration to orchestrate realistic datasets for finance, healthcare, and other regulated environments.
MIT ★ 117 -
Turn OpenAPI contracts into deterministic, stateful virtual services, synthetic test data, and validation evidence—with REST, MCP, and a local AI Copilot.
pypi MIT -
Independent student demo: an MCP server on synthetic dental-plan data that lets an AI agent verify benefits for a batch of patients, with plan-clause citations and a human review queue.
MIT -
Multi-agent football broadcast crew on Microsoft Agent Framework: two AI writers, a rule-based Compliance gate, kill-and-recover, What-If simulations. Synthetic data, fictional clubs.
MIT -
crm-mcp-agent-publicgithub.com/euuuuuuan/crm-mcp-agent-publicupdated this year
An agent does a CRM marketer's ad-hoc SQL over 5 read-only MCP tools against a deterministic synthetic CDP, behind a pure-stdlib governance kernel: tiered authority, fingerprint-bound approvals, a kill switch, and caps derived from the audit log. 45 adversarial tests. All data is 100% synthetic and campaign send is a simulator.
Apache-2.0 -
Hierarchical Bayesian MMM, geo matched-market tests, spot-level TV response and a harmonization layer, with a results API and MCP server. Python, NumPyro, Postgres. Synthetic data.
MIT -
real-fake-data-mcpgithub.com/przeslijmi/real-fake-data-mcpupdated this year
MCP server for Real Fake Data — realistic synthetic test data for AI assistants
npm MIT -
@aetherya/mcpactive
Aetherya MCP server: test decisions on a synthetic audience from any MCP agent. Run research studies, site audits, copy tests, instant market reads and post or email simulations, then get a decision brief. Simulated, not real-user data.
npm MIT -
MCP server and guarded agent loop for data-quality checks on synthetic claims tables
-
Official MCP Python server exposing typed data-engineering tools, resources, prompts, read-only SQL, and synthetic ETL investigations.
-
seedforgegithub.com/cognis-digital/seedforgeupdated this year
Synthetic test-data generator with referential integrity
NOASSERTION -
com.weavori/mcpno update data
Generate referentially intact, distribution-realistic PostgreSQL synthetic data from AI assistants.
npm -
human-mcpgithub.com/dvelton/human-mcpupdated this year
A person-centric rather than a service-centric MCP server. Thought experiment with synthetic data.
★ 2 -
Example of an MCP server for data query and analysis on synthetic supermarket database
★ 1 -
Payment MCP Lab — TypeScript tools, resources and prompts over synthetic in-memory payment data.
-
Read-only Python MCP server for investment report search, financial metrics, and source-cited comparisons. 50 verification checks on synthetic data.
-
Governed incident response for a synthetic data platform: MCP, PydanticAI and Temporal with signed approvals, idempotent effects and reproducible evidence.
Apache-2.0 ★ 1 -
Universal schema compiler (SQL/Prisma to Zod, TypeScript, Pydantic) and realistic synthetic mock API data generator for MCP.
MIT -
fof-mcp-demogithub.com/cynthiacxzhang/fof-mcp-demoupdated this year
Flow-of-Funds MCP server demo: Hive/Trino-style schema, query, and analysis tools over synthetic banking transaction data
-
MCP server extending SuperMemory with medical image embedding (DenseNet) and similar-case search; synthetic-data demo.
★ 1 -
Deterministic synthetic data generator for realistic, correlated, and noisy test records across 68 locales. Rust CLI/Python/Node.js/Browser WASM/Go/PHP/Ruby/MCP
NOASSERTION ★ 25 -
custodian-mcpgithub.com/Zacplischka/custodian-mcpupdated this year
Governed agent-memory MCP server — fail-closed auth, strict multi-tenant isolation, audited authorization. Synthetic-data demonstration.
MIT ★ 1 -
MCP-powered marketing campaign review: deterministic checks plus an evidence-validated LLM reviewer. Synthetic data, demo only.
MIT -
MRI prior-authorization assistant: LangGraph + MCP + Claude, with a human in the loop. Synthetic data.
MIT -
Let an AI agent work with your data without seeing it: value-free schemas, synthetic data, text anonymization and pseudonymization, with an MCP server and Claude Code guard.
MIT ★ 1 -
AI agent drafts QA scores via MCP tools; guardrails validate; humans approve in a review queue. Golden-set eval. Synthetic data.
MIT -
MCP add-on for Alexa+ with an Alexa+ behavior simulator (Amazon Developer Hackathon 2026, synthetic data only)
MIT -
Google Ads MCP server + analytics toolkit in Python: weekly monitoring, CPC root-cause diagnostics, and automated dashboards. Sanitized portfolio showcase (synthetic data, no credentials).
-
Microsoft Fabric enterprise BI reference build: hot and cold paths, medallion Lakehouse, semantic model, governed data agent (MCP + A2A), Purview-style governance, Terraform + Bicep. Runs offline on synthetic data.
MIT -
7 insurance-ops automation projects: bordereaux standardisation, data-quality controls and ledger reconciliation, complaints triage with human review, an MCP server, an agent tool-routing eval harness and Claude Code hooks. Synthetic data.
-
NBA basketball-team use-case follow-up to a C# Parquet MCP server: player analytics, synthetic data, weighted shooting calculations and tests.
-
Voice-first factory-floor co-pilot with self-hosted MCP tools, persistent handovers and synthetic production data.
MIT -
agentgovgithub.com/bdeva1975/agentgovupdated this year
Governance & observability control plane for agentic systems — policy/budget enforcement, audit trail, and MCP integration. Synthetic-data POC.
MIT -
Enterprise device analytics with a governed AI assistant: DuckDB medallion pipeline, read-only MCP tools for Claude, evals, human-approved briefings and a live React app. Synthetic data.
-
Flight ops SRE agent on Amazon Bedrock AgentCore with an MCP server. Runs offline with synthetic data; deploy and cleanup scripts included.
MIT -
fhir-mcp-servergithub.com/alewalsh/fhir-mcp-serverupdated this year
A C#/.NET MCP server that exposes read-only clinical tools over synthetic FHIR patient data for Claude
MIT ★ 1 -
Give AI agents safe, read-only access to one patient's FHIR health records over MCP. Prototype, synthetic data.
Apache-2.0 -
A Python-based MCP server implementing causal inference analysis on synthetic customer spending data. Uses DoWhy for causal effect estimation and FastMCP for exposing causal tools. Enables interactive causal analysis with treatment and outcome variables from program signup data.
-
Read-only MCP server (C#/.NET 8) that lets Claude query a SQL Server through approved views only. Synthetic data, reference build.
MIT -
Care handoffs with no silent transfer of responsibility: self-hosted MCP server (spec 2025-11-25, Streamable HTTP) + MCP Apps dashboard. Simulated Alexa+ workflow, synthetic data.
MIT -
timeweaver-mcpgithub.com/FixtureForge/timeweaver-mcpupdated this year
Synthetic time-series test data generator — an MCP server that creates realistic series with trend, seasonality, noise, and anomalies for testing dashboards, monitoring, and forecasting. For Claude, Cursor, and any MCP client.
npm -
Agentic supply-execution copilot: MCP + LangGraph + evals, on synthetic data
MIT -
Hosted MCP server for FHIR R4 health data: connect Claude, Cursor or VS Code to 30 synthetic patients, IPS, patient context, FHIR search and lab import. Official MCP Registry: com.anpheros/fhir.
Apache-2.0 -
Declarative synthetic data for Python. State the facts a dataset must hold (monthly revenue, channel shares, balanced ledgers, foreign keys, state machines) and get multi-table data that holds them exactly, with a DuckDB certificate anyone can rerun. From YAML, SQL DDL or a sentence. CLI and MCP server.
pypi MIT ★ 77 -
FinanceOps Copilot — local AI agent connecting ERPs via MCP, with RAG over finance policies and finance-department automation. Architectural showcase (sanitized prototype, synthetic data).
MIT -
A governed MCP server: canonical, provenance-stamped answers for business metrics over role-based access, with a lexer-guarded ad-hoc path and a full audit trail. Architecture, decision records and a working reference implementation on synthetic data.
CC-BY-4.0 -
MCP server that triages a Jira board with typed, calibrated decisions from a small local model — confidence, human-review flags, held-out evaluation. Synthetic bank-themed data.