multidim-mcp
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., "@multidim-mcp Analyze the OAuth2 migration with a decision lens"
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.
multidim-mcp
Structured thinking grids for AI agents — a standalone MCP server, pure standard library.
Multidim routes a subject to a set of analysis lenses (a context) and returns a hierarchical grid — axes, sub-lenses, mandatory questions — for the calling LLM to fill in. The thinking stays with the caller: the server provides structure, never cognition. It calls no LLM, makes no network requests, and the same input always produces the same frame.
Zero dependencies — Python 3.9+, standard library only.
Deterministic v2 contract — every frame carries a self-verifiable
frame_hash; a filled analysis is checked section by section with actionable error codes.Learned traps — lessons you record once become mandatory questions injected into every future frame whose subject matches.
Hardened store — atomic writes, native cross-process locking, additive migrations, backed-up resets, and a guard that refuses to ever touch a foreign
~/.multidimstore.
See the difference
An agent analyses "Should we migrate the billing service from MySQL to
PostgreSQL?". Every section is filled, every sentence reads fine. Here is what
multidim_validate returns on that first pass:
overall verdict: REJECT
REJECT alternatives NOT_ENOUGH_ALTERNATIVES, ALTERNATIVE_DUPLICATES_PRIMARY
REJECT hypotheses HYPOTHESIS_NOT_FALSIFIABLE
REJECT second_order_risks SECOND_ORDER_REPEATS_FIRST
REJECT cross_talk GENERIC_DENSITY_HIGH
REJECT synthesis SYNTHESIS_WITHOUT_REFERENCES
WARNING premortem PREMORTEM_SIMILAR_TO_RISKSThe only alternative restated the hypothesis, the hypothesis carried no test that could prove it wrong, the second-order effect repeated the first one word for word, and the conclusion referenced none of the work above. None of that is visible when you read the answer; all of it is reported here, by name.
Redo the rejected sections and the same checker returns ACCEPT. Edit the frame
to delete the rule you find inconvenient, and it refuses the whole submission —
the frame carries a hash of its own content.
Full transcript, including what the fixed sections look like and what this
deliberately does not check: DEMO.md. Reproduce it in one
command: python demo.py.
Related MCP server: CRASH - Cascaded Reasoning with Adaptive Step Handling
Quickstart
pip install multidim-mcp # from PyPI
pip install . # or from a source checkoutRegister the server with any MCP client (stdio transport):
{
"mcpServers": {
"multidim": {
"command": "multidim-mcp"
}
}
}Or run it directly: python -m multidim_mcp, or without installing: uvx multidim-mcp.
The server is listed in the official MCP Registry as
io.github.Cherridsaid/multidim-mcp.
Tools
Tool | Role |
| Build the grid for a subject ( |
| List every known context with its axes and sub-lenses |
| Deterministic, stateless check of a filled analysis against its v2 frame — |
| Create or enrich a context (keywords, axes, traps) — the only write door |
How it works
multidim_analyzedetects the best context for your subject (word-boundary keyword matching, accent-folded) and returns a v2 frame: required sections, section schemas, validation rules, mandatory questions — including every learned trap whose triggers match the subject.Your LLM fills the frame, section by section.
multidim_validaterebuilds the frame from the store, refuses a tampered or stale one (frame_hash), then checks the analysis: structural completeness, falsification tests on hypotheses, alternatives that genuinely differ from the primary, second-order effects distinct from first-order, a pre-mortem that does not copy the risk list, a synthesis that references real identifiers, and a filler-phrase density cap. Only rejected sections are redone, within the frame'smax_validation_rounds.
The four seed contexts are neutral and deterministic: generic (8 general
lenses), code_review, technical_writing, decision.
Storage
The store lives on a dedicated per-user data path (MULTIDIM_MCP_HOME overrides
it) and is created on first run from the neutral seeds. Writes are atomic and
serialized across processes with the OS's native file locking; a corrupt store is
backed up before any reset, never silently discarded. A tripwire refuses every
read or write that would resolve into a foreign personal ~/.multidim store.
Maintainers publishing forks can extend the neutrality guard with their own
private markers via MULTIDIM_MCP_EXTRA_FORBIDDEN (comma-separated), without
hardcoding them into public source.
Transparency
Not an AI system. multidim-mcp contains no model and performs no inference: it is deterministic, rule-based software. Under the EU AI Act (Reg. 2024/1689) it is not an AI system in the sense of Art. 3(1), and as free and open-source software it falls under the Art. 2(12) exemption. It collects no data and makes no network calls.
Illustrations in this README were generated with GPT and keep their C2PA provenance metadata intact.
Development
python run_tests.py # full suite, stdlib only
python smoke_install.py # packaging smoke test (wheel + venv + entry point)
python demo.py # the analyse -> validate -> fix -> accept cycle of DEMO.mdCI runs both on Ubuntu and Windows across Python 3.9 / 3.11 / 3.13.
License
Available Tools
4 toolsmultidim_analyzeA
Build a hierarchical multidimensional grid (axes -> sub-lenses) adapted to the subject's context. Returns the grid to fill, not the analysis.
Inputs: subject (required), depth, format, context.
multidim_contextsA
List every known context with its axes and sub-lenses.
Inputs: no named parameters.
multidim_learnA
Create or enrich a context. Use only to promote a lens reusable beyond the current subject: deliberate promotion, never automatic. Persists to the dedicated store (the only write door).
Inputs: context (required), axes, traps, keywords, +1 more.
multidim_validateA
Deterministic, STATELESS check of a filled analysis against its v2 frame (multidim_analyze format v2). Returns an ACCEPT / WARNING / REJECT verdict per section with actionable error codes. Never modifies the store, calls no LLM, never judges the truth of the content: structure, internal consistency and checkable requirements only. The calling LLM redoes ONLY the rejected sections, within the frame's max_validation_rounds (tracked by the caller).
Inputs: frame (required), analysis (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 4 tools
Each tool has a unique, clearly defined purpose: analyze creates a grid, contexts lists them, validate checks structure, and learn writes. No overlapping responsibilities.
All tools share the 'multidim_' prefix, but 'multidim_contexts' uses a noun instead of a verb_noun pattern while others use verbs (analyze, validate, learn). Minor inconsistency.
With only 4 tools, the server is tightly scoped for its domain. The count is low but appropriate for a focused multidimensional analysis framework, not over- or under-inclusive.
The tools cover the core lifecycle: creating/analyzing, listing, validating, and learning. There is no explicit delete, but 'learn' can enrich or create, and the set appears sufficient for the stated purpose.
Maintenance
Related MCP Connectors
Paid deterministic data-quality and execution-verification tools for AI agents.
Deterministic reasoning stack for AI agents: simulate, decide & compute, plus cross-domain tools.
15 deterministic validation tools for AI agents: tax IDs (15 countries), VAT, IBAN, LEI, HS codes.
Deterministic validation for AI-generated artifacts: JSON Schema, OpenAPI response, SQL syntax.
Related MCP Servers
- AlicenseBqualityNot gradedmaintenanceProvides structured sequential thinking capabilities for AI assistants to break down complex problems into manageable steps, revise thoughts, and explore alternative reasoning paths.29-
- AlicenseAqualityDmaintenanceEnables structured, iterative reasoning for complex problem-solving with features like confidence tracking, revision mechanisms, and branching support. Provides flexible validation and multiple output formats for systematic analysis and decision-making tasks.1111 npm72MIT
- AlicenseBqualityDmaintenanceProvides AI systems with structured thinking frameworks and reasoning tools to maintain consistent problem-solving patterns across conversations. Enables multi-step reasoning, decision analysis, and systematic troubleshooting through invocable mental models.1543 npm20MIT

Agent Toolsofficial
AlicenseNot gradedqualityDmaintenanceProvides deterministic tools for transforming, formatting, and inspecting structured data for AI agents.11 npm19Apache 2.0