Euclid-MCP

MCP server for logical reasoning — turns facts into formal proofs.

Euclid-MCP is a hybrid cognitive architecture: a lightweight LLM describes the world in facts, and a deterministic engine performs the actual deduction. The LLM never needs to reason — it only needs to describe.

With Euclid-MCP, an 8B model can solve reasoning tasks that stump even 400B+ cloud models — because the engine handles deduction deterministically. Every answer comes with a proof tree, so you can trace why a conclusion holds, not just what it is. Use it to enforce RBAC policies, audit cloud compliance, validate loan eligibility rules, or reason over any domain where answers must be explainable and verifiable.

euclid-cli session: diagnose why bob cannot deploy, then enable it with a what-if role grant

Euclid-MCP is written in Python and uses Euclid-IR, a human-readable intermediate language designed for both AI agents and humans. It uses SWI-Prolog as its primary inference engine — and, where SWI-Prolog is not available (e.g. minimal containers), a pure-Python native engine that interprets Euclid-IR directly (see docs/NATIVE_ENGINE.md). It can be consumed in multiple ways: via MCP by AI agents (OpenCode, Claude, Cursor), via HTTP by tools and automation platforms (n8n, Zapier, Make), and via Python API for direct integration. Euclid-IR rules can also be used to augment RAG pipelines with deterministic policy enforcement.

How it works

Code

┌──────────────┐     ┌──────────────────┐     ┌──────────────┐     ┌─────────────────┐
│  LLM/Agent   │────▶│  Euclid-MCP      │────▶│  Translator  │────▶│  SWI-Prolog     │
│  (MCP Client)│◀────│  (MCPServer)     │◀────│  + Meta-IP   │◀────│  (persistent)   │
└──────────────┘     └──────────────────┘     └──────────────┘     └─────────────────┘

Receive facts, rules, and a query in a simple intermediate language
Translate into Prolog with a meta-interpreter for proof tree capture
Execute via a persistent SWI-Prolog engine process (JSON-lines protocol on stdin/stdout; the workspace is reloaded per call, no process spawn overhead)
Return solutions + proof trees as structured JSON

Additional tools (explain, diagnose, what_if, check_kb) extend this core flow with natural-language explanations, analysis, scenario testing, and validation.

LLMs describe. Euclid MCP proves.

Knowledge Base

For small knowledge bases, facts and rules can be provided with each request.

A knowledge base can be loaded at server startup and reused across calls, so agents only pass the session-specific facts for the current query. This minimizes token usage, improves performance, and allows small LLMs to reason over large rule sets without reconstructing the entire knowledge base for every request.

Intermediate Language

Even if currently Euclid-MCP uses a Prolog Engine, no Prolog syntax is required.
Euclid-IR (Intermediate Representation) is a declarative intermediate representation for logical inference. Variables use $name, implication is IF, conjunction is AND.

Text format:

Code

human(socrates)
mortal($x) IF human($x)

? mortal($who)

YAML format:

yaml

facts:
  - parent(tom, bob)
  - parent(bob, ann)
  - parent(tom, liz)
rules:
  - ancestor($x, $y) IF parent($x, $y)
  - ancestor($x, $y) IF parent($x, $z) AND ancestor($z, $y)

query: ancestor(tom, $who)

Full language reference: docs/EUCLID_IR.md

Euclid-IR Syntax Reference

Element	Syntax	Example
Facts	`predicate(args)`	`parent(tom, bob)`
Variables	`$name` (lowercase)	`$who`, `$x`, `$count`
Implication	`IF`	`mortal($x) IF human($x)`
Conjunction	`AND`	`p($x) AND q($x)`
Negation	`NOT`	`NOT active($user)`
Boolean literals	`true` / `false` in rule bodies	`merchant($m) IF false`
Query	`? predicate`	`? ancestor(tom, $who)`
String literals	`"..."` or `'...'`	`"alice@example.com"`
Multi-line rules	Body on next line	`rule($x) IF\n body($x)`

Arithmetic Comparisons

Rules support arithmetic comparisons that are evaluated during deduction:

Code

# Stale access: users who haven't logged in for 90+ days
stale_access($user) IF
    user($user) AND last_login_days($user, $days) AND $days > 90

# Excessive permissions: more than 15 direct permissions
excessive_permissions($user, $count) IF
    user($user) AND permission_count($user, $count) AND $count > 15

# Clearance check: user clearance >= resource classification
can_access($user, $resource) IF
    user($user) AND resource($resource, _, _, _, _, $cls) AND
    classification($cls, $cls_level, _) AND
    user_clearance($user, $user_level) AND $user_level >= $cls_level

Supported operators: >, >=, <, <=, ==, is, !=

Multi-line Rules

Rules can span multiple lines for readability:

Code

can_deploy($user, $env) IF
    user($user) AND
    has_role($user, $role) AND
    deploy_requires_level($env, $min) AND
    deploy_role_level($role, $level) AND
    $level >= $min AND
    user_has_permission($user, deploy_code)

Conjunctions in Queries

Queries can combine multiple predicates:

Code

? can_access_resource($who, $res) AND resource($res, _, _, _, _, secret)

This returns solutions where both conditions are satisfied simultaneously.

Why External Inference?

The external inference gives several advantages:

deterministic
explainable
verifiable
inexpensive
replaceable backend

In the current implementation Euclid-MCP uses Prolog.
Prolog is a 50-year-old battle-tested logic engine. Using it as a "deduction coprocessor" lets small LLMs perform complex multi-step reasoning without needing larger, more expensive models. The intermediate language strips away Prolog's syntax quirks while keeping its logical core.

A specific benchmark demonstrate the difference: with 1 000+ facts, LLMs alone score 2/5 while Euclid-MCP scores 5/5 — and runs 7× faster while outputting 14× fewer tokens.

Tools

Euclid-MCP exposes 8 tools, each with a specific purpose:

Tool	Purpose
`reason`	Main deduction — get solutions + proof trees
`explain`	Readable, natural-language reasoning steps
`diagnose`	Understand why a query succeeds or fails
`what_if`	Test modifications before applying them
`check_kb`	Validate KB consistency before reasoning
`register_kb`	Register a named KB under a `kb_id`
`unregister_kb`	Remove a named KB from the registry
`list_kbs`	List registered named KBs (metadata)

`reason`

Main tool for verifiable deterministic reasoning.

Parameter	Type	Default	Description
`knowledge`	`string?`	—	Facts & rules in text or YAML format
`kb_id`	`string?`	—	Reference a KB registered via `register_kb`
`delta_knowledge`	`string?`	—	Session-specific facts appended to the `kb_id` base
`query`	`string?`	—	Override query (optional)
`max_solutions`	`int`	`5`	Max solutions to return
`max_depth`	`int`	`30`	Max proof tree depth

Returns ReasonResult with solutions[] — each containing variable bindings and a proof tree.

`explain`

Deterministic proof-tree → natural-language reasoning steps. No LLM involved: it walks the proof tree of each solution and renders every step in plain language, citing the rule ID (# RULE: <id>) when a rule has one. Use it to turn a proof into an auditable, human-readable explanation.

Parameter	Type	Default	Description
`knowledge`	`string?`	—	Facts & rules in text or YAML format
`kb_id`	`string?`	—	Reference a KB registered via `register_kb`
`delta_knowledge`	`string?`	—	Session-specific facts appended to the `kb_id` base
`query`	`string?`	—	Override query (optional)
`max_solutions`	`int`	`5`	Max solutions to return
`max_depth`	`int`	`30`	Max proof tree depth

Returns ExplanationResult with explanations[] — each containing variable bindings, an ordered list of natural-language steps, and language-independent structured_steps (typed kind/goal/rule_id/body, ready for localized rendering in a UI).

`diagnose`

Query analysis — understand why a query succeeds or fails.

Parameter	Type	Default	Description
`knowledge`	`string?`	—	Facts & rules in text or YAML format
`kb_id`	`string?`	—	Reference a KB registered via `register_kb`
`delta_knowledge`	`string?`	—	Session-specific facts appended to the `kb_id` base
`query`	`string`	—	Query to diagnose
`mode`	`string`	`why`	One of: `why`, `why_not`, `what_needs`
`max_solutions`	`int`	`5`	Max solutions to return
`max_depth`	`int`	`30`	Max proof tree depth

Modes:

why — explain why a query holds (or that it doesn't)
why_not — explain why a query fails (missing facts/rules)
what_needs — suggest what would make a false query true

Returns DiagnosisResult with holds, findings[], conclusion, and optionally proof.

`what_if`

Scenario analysis — apply modifications to a knowledge base and compare results.

Parameter	Type	Default	Description
`base_knowledge`	`string?`	—	Base facts & rules
`kb_id`	`string?`	—	Reference a KB registered via `register_kb`
`delta_knowledge`	`string?`	—	Session-specific facts appended to the `kb_id` base
`modifications`	`string`	—	`+ fact(...)` to add, `- fact(...)` to remove
`query`	`string`	—	Query to evaluate
`max_solutions`	`int`	`5`	Max solutions to return
`max_depth`	`int`	`30`	Max proof tree depth

Returns WhatIfResult with before_count, after_count, delta, solutions_before, solutions_after, conclusion.

`check_kb`

Knowledge base validator — check for consistency before running deduction.

Parameter	Type	Default	Description
`knowledge`	`string?`	—	Facts & rules in text or YAML format
`kb_id`	`string?`	—	Reference a KB registered via `register_kb`
`delta_knowledge`	`string?`	—	Session-specific facts appended to the `kb_id` base

Returns KBCheckResult with valid, errors[], warnings[], facts_count, rules_count, predicates_count, and predicates[] — the predicate inventory (name → arities, facts, rules counts) that doubles as the contract for LLM extraction.

KB identity in results

Every tool result — ReasonResult, ExplanationResult, DiagnosisResult, WhatIfResult, and KBCheckResult — carries two identity fields:

Field	Value
`content_hash`	sha256 of the KB text payload (the exact source that was reasoned over)
`version`	the `@version` directive of the KB, or `null` when absent

The fields are present on every return path, including error branches, so a result can always be pinned to the exact KB it was computed from: anyone with the .euclid text and Euclid-MCP can recompute the hash and verify it. This is the foundation for KB versioning, signatures, and audit trails built on top of the engine.

config.json

{
  "query": "mortal($who)",
  "solutions": [...],
  "elapsed_ms": 12.4,
  "content_hash": "a3f9c1e4b82d55f0…",
  "version": "1.0"
}

KB Preload

A knowledge base can be loaded once at server startup and reused across calls, so agents only pass the session-specific facts for the current query.

Preload a KB by file path, via the EUCLID_KB_PATH environment variable or a --kb-path CLI flag:

bash

# Environment variable
EUCLID_KB_PATH=/path/to/policies.euclid python3 -m euclid_mcp

# CLI flag (MCP stdio, console script, and HTTP API)
python3 -m euclid_mcp --kb-path /path/to/policies.euclid
python3 integrations/euclid_api.py --kb-path /path/to/policies.euclid --port 8080

Behavior:

The file is validated with check_kb at startup and the server fails fast with a clear message if the file is missing, unreadable, oversized, or invalid.
knowledge/base_knowledge on reason, explain, diagnose, what_if, and check_kb become optional: an explicit value always wins, an empty value falls back to the preloaded KB. With neither, tools return a clear "No knowledge provided" error.
A markdown digest of the preloaded KB (fact/rule/predicate counts, predicate inventory, rules with their IDs) is appended to the server instructions, so agents can see what the KB covers without extra tool calls.

Backward compatible: passing knowledge explicitly behaves exactly as before.

Named KBs (`kb_id` + `delta_knowledge`)

A KB can also be registered once under a kb_id and then referenced on every call without resending the text — the in-memory registry is per server instance, so replicas re-register their KBs on startup (matching the scale-out model of the HTTP API). Up to 32 KBs per instance; register_kb overwrites an existing kb_id (update semantics for idempotency).

python

# Register once — validated with check_kb first
register_kb(kb_id="rbac-policy", knowledge="has_role(alice, admin) ...\n? $role ...")

# Reference it on every call
result = reason(kb_id="rbac-policy", query="can_deploy($user, prod)")

# Session-specific facts on top of the registered base (no re-registration):
result = reason(
    kb_id="rbac-policy",
    delta_knowledge="has_role(alice, dev)\nhas_env(dev, staging)",
    query="can_deploy($user, staging)",
)

register_kb(kb_id, knowledge) — validates the kb_id (allowlist [a-z0-9_-]{1,64}) and the KB (check_kb), then stores it. Returns the record: registered, kb_id, content_hash, version, facts, rules, predicates. Unknown ids are rejected; a full registry returns an error.
unregister_kb(kb_id) — removes the KB; returns removed: true/false.
list_kbs() — lists registered KBs (metadata only, no source text).

Resolution precedence on reason, explain, diagnose, what_if, check_kb: explicit knowledge/base_knowledge wins → else kb_id (unknown id → Unknown kb_id: <id>; delta_knowledge is concatenated to the registered source) → else the EUCLID_KB_PATH preload → else a clear "No knowledge provided" error. delta_knowledge without a kb_id is an error. content_hash/version on a kb_id result are computed from the effective source (base + delta), so a result can always be pinned to the exact text reasoned over.

The HTTP API exposes the same flow as POST /register-kb, POST /unregister-kb, and POST /list-kbs.

Installation

pip

bash

# Prerequisite: Python ≥ 3.10

# SWI-Prolog (for better performances)
brew install swi-prolog

# Install
pip install euclid-mcp

From source

bash

git clone https://github.com/meob/Euclid-MCP
cd Euclid-MCP
python3 -m venv .venv && source .venv/bin/activate
pip install -e .

Docker

No local SWI-Prolog installation needed — the image bundles everything.

bash

# Build
docker build -t euclid-mcp .

# MCP stdio mode (for local MCP clients)
docker compose run --rm euclid-mcp

# HTTP API mode (for n8n, Zapier, remote access)
docker compose up euclid-api
# API available at http://localhost:8080

See Docker in Integrations for full details.

Usage

Via MCP (OpenCode, Claude, etc.)

config.json

{
  "mcpServers": {
    "euclid-mcp": {
      "command": "python3",
      "args": ["-m", "euclid_mcp"],
      "cwd": "/path/to/euclid-mcp"
    }
  }
}

Via Python

server.ts

from euclid_mcp.server import reason, explain, diagnose, what_if, check_kb

# Reasoning
result = reason(knowledge="""
    human(socrates)
    mortal($x) IF human($x)
    ? mortal($who)
""")
for sol in result.solutions:
    print(sol.substitutions, sol.proof.type)

# Explanation — readable reasoning steps (cites rule IDs when present)
expl = explain(
    knowledge="human(socrates)\nmortal($x) IF human($x)  # RULE: BIO-001",
    query="mortal($who)"
)
for e in expl.explanations:
    print(e.substitutions, e.steps)
    print(e.structured_steps)  # typed, language-independent steps

# Diagnosis — why does a query fail?
diag = diagnose(
    knowledge="human(socrates)\nmortal($x) IF human($x)",
    query="mortal(plato)",
    mode="why_not"
)
print(diag.conclusion)

# What-if — how does adding a fact change results?
scenario = what_if(
    base_knowledge="human(socrates)\nmortal($x) IF human($x)",
    modifications="+ human(plato)",
    query="mortal($who)"
)
print(f"Before: {scenario.before_count}, After: {scenario.after_count}")

# KB validation
check = check_kb(knowledge="human(socrates)\nmortal($x) IF human($x)")
print(f"Valid: {check.valid}, Errors: {check.errors}")

Via CLI

The euclid-cli command wraps the five reasoning tools (reason, explain, diagnose, what_if, check_kb) for the terminal. It reads the KB from a .euclid file (-f), inline (--knowledge), or falls back to EUCLID_KB_PATH/preload, and selects the backend with --backend (auto | prolog | native). Queries come from --query or from the ? lines inside the KB file.

Run with no subcommand to open an interactive Euclid-IR REPL — type facts, rules and ? query lines directly, like you would in swipl or psql. The session knowledge base accumulates across queries.

bash

$ euclid-cli
Euclid-MCP REPL — type facts and rules in Euclid-IR, then `? query`.
Commands: :help  :check  :kb  :load  :explain  :diagnose  :what-if  :reset  :quit

euclid > human(socrates)
euclid > mortal($x) IF human($x)
euclid > ? mortal($who)
Query: mortal($who)
Solution 1:
  who: socrates
mortal(socrates)  [rule]
  human(socrates)  [fact]

euclid > :what-if + human(plato)
Solutions: 1 -> 2 (delta: more)
euclid > :quit

REPL meta-commands: :check, :kb, :load <file>, :explain [query], :diagnose <query> [why|why_not|what_needs], :what-if <mods>, :reset, :quit. Multi-line rules continue after IF/AND (prompt becomes ... >). Piped input runs the same loop as a batch script without prompts:

bash

printf 'human(socrates)\nmortal($x) IF human($x)\n? mortal($who)\n' | euclid-cli

bash

# Validate a knowledge base
euclid-cli check -f policies.euclid

# Run a deduction (query taken from the ? line in the file)
euclid-cli reason -f policies.euclid

# Explicit query + limits
euclid-cli reason -f policies.euclid --query "can_deploy($user, prod)" \
    --max-solutions 10 --max-depth 40

# Inline KB (no file)
euclid-cli reason --knowledge "human(socrates)
mortal(\$x) IF human(\$x)
? mortal(\$who)"

# Readable reasoning steps
euclid-cli explain -f policies.euclid

# Why does a query fail?
euclid-cli diagnose -f policies.euclid --query "can_deploy(bob, prod)" \
    --mode why_not

# What-if: how does adding a fact change the answer?
euclid-cli what-if -f policies.euclid \
    --modifications "+ has_role(bob, deployer)" --query "can_deploy(bob, prod)"

# Force the pure-Python native engine (no SWI-Prolog)
euclid-cli --backend native reason -f policies.euclid

# Machine-readable output
euclid-cli reason -f policies.euclid --json

Exit codes: 0 on success, 1 when the tool reports an error (including an invalid KB from check), 2 on usage errors.

Full CLI reference (all flags, backends, JSON output): docs/CLI.md

Example output

config.json

{
  "query": "ancestor(tom, $who)",
  "solutions": [
    {
      "substitutions": {"who": "bob"},
      "proof": {
        "type": "rule",
        "goal": "ancestor(tom, bob)",
        "body": "parent(tom, bob)",
        "rule_id": "GEN-1",
        "subproof": {"type": "fact", "goal": "parent(tom, bob)"}
      }
    },
    {
      "substitutions": {"who": "ann"},
      "proof": {
        "type": "rule",
        "goal": "ancestor(tom, ann)",
        "body": "parent(tom, bob), ancestor(bob, ann)",
        "rule_id": "GEN-2",
        "subproof": {
          "type": "and",
          "left": {"type": "fact", "goal": "parent(tom, bob)"},
          "right": {
            "type": "rule",
            "goal": "ancestor(bob, ann)",
            "body": "parent(bob, ann)",
            "rule_id": "GEN-1",
            "subproof": {"type": "fact", "goal": "parent(bob, ann)"}
          }
        }
      }
    }
  ]
}

Rules can carry an audit-trail ID via a trailing # RULE: <id> comment; the ID is surfaced as rule_id on the rule nodes of the proof tree, so a decision can be cited ("this derives from rule GEN-2").

Diagnose output

config.json

{
  "query": "mortal(plato)",
  "mode": "why_not",
  "holds": false,
  "findings": [
    {
      "type": "satisfied",
      "predicate": "human",
      "detail": "Facts exist for 'human' (1 facts)"
    }
  ],
  "conclusion": "The query fails. Check rule conditions."
}

What-if output

config.json

{
  "query": "mortal($who)",
  "modifications": "+ human(plato)",
  "before_count": 1,
  "after_count": 2,
  "delta": "more",
  "solutions_before": [{"substitutions": {"who": "socrates"}}],
  "solutions_after": [
    {"substitutions": {"who": "plato"}},
    {"substitutions": {"who": "socrates"}}
  ],
  "conclusion": "Solutions increased: 1 -> 2."
}

Explain output

config.json

{
  "query": "mortal($who)",
  "explanations": [
    {
      "substitutions": {"who": "socrates"},
      "steps": [
        "mortal(socrates) is derived by rule BIO-001 from: human(socrates).",
        "human(socrates) is asserted as a fact in the knowledge base."
      ]
    }
  ]
}

Use cases

Small LLM reasoning: Offload deduction from LLMs (3-8B) to a deterministic engine
Explainable decisions: Every answer comes with a proof tree which allows explanation, reasoning trace, and justification
Business rules: Validate logic chains (permissions, workflows, compliance)
Dependency analysis: Circular dependency detection, topological ordering
Education: Interactive logic tutoring with visible proof chains (see docs/DIDACTIC.md, a step-by-step teaching guide built around the euclid-cli REPL)
Knowledge preload: Complex business rules can be loaded in Euclid instead of using a vector database
Query diagnosis: Understand why queries fail and what facts/rules are missing
Scenario analysis: Test "what-if" modifications before applying them to production
KB validation: Check knowledge bases for consistency before reasoning

Real-world examples

There are several examples provided as samples: Genealogy, RBAC, Classification, Loan Eligibility, Cluedo Detective, IT Security & Compliance, LLM vs Euclid-MCP, ... Most interesting ones are the IT Security & Compliance (with CIS, AWS, IAM Standards enforcement, Company Policies implementation, hundreds of Data Facts) and side-by-side LLM vs Euclid-MCP.

Examples full description: docs/EXAMPLES.md

Integrations

OpenCode

Euclid-MCP includes a pre-configured agent in .opencode.json:

config.json

{
  "mcpServers": {
    "euclid-mcp": {
      "command": "python3",
      "args": ["-m", "euclid_mcp"],
      "cwd": "."
    }
  },
  "agents": {
    "reasoning-engine": {
      "description": "Deterministic logic engine",
      "instructions": "Write facts in Euclid IR, use the reason tool...",
      "mcpServers": ["euclid-mcp"]
    }
  }
}

n8n / Zapier / Make

Run the HTTP API:

bash

python3 integrations/euclid_api.py --port 8080

Endpoint	Method	Purpose
`/reason`	POST	Deduction with proof trees
`/explain`	POST	Natural-language reasoning steps
`/diagnose`	POST	Query failure analysis
`/what-if`	POST	Scenario testing
`/check-kb`	POST	KB validation
`/register-kb`	POST	Register a named KB (`kb_id`)
`/unregister-kb`	POST	Remove a named KB
`/list-kbs`	POST	List registered named KBs
`/health`	GET	Health check (deep: pings the engine; 503 only when wedged)
`/metrics`	GET	Prometheus metrics (open, read-only, never KB content)

bash

# Reasoning
curl -X POST http://localhost:8080/reason \
  -H "Content-Type: application/json" \
  -d '{"knowledge": "human(socrates)\nmortal($x) IF human($x)\n? mortal($who)"}'

# Explanation
curl -X POST http://localhost:8080/explain \
  -H "Content-Type: application/json" \
  -d '{"knowledge": "human(socrates)\nmortal($x) IF human($x)\n? mortal($who)"}'

# Diagnosis
curl -X POST http://localhost:8080/diagnose \
  -H "Content-Type: application/json" \
  -d '{"knowledge": "human(socrates)\nmortal($x) IF human($x)", "query": "mortal(plato)", "mode": "why_not"}'

# What-if
curl -X POST http://localhost:8080/what-if \
  -H "Content-Type: application/json" \
  -d '{"base_knowledge": "human(socrates)\nmortal($x) IF human($x)", "modifications": "+ human(plato)", "query": "mortal($who)"}'

# KB validation
curl -X POST http://localhost:8080/check-kb \
  -H "Content-Type: application/json" \
  -d '{"knowledge": "human(socrates)\nmortal($x) IF human($x)"}'

# Register a named KB once, then reference it by kb_id
curl -X POST http://localhost:8080/register-kb \
  -H "Content-Type: application/json" \
  -d '{"kb_id": "rbac", "knowledge": "human(socrates)\nmortal($x) IF human($x)"}'

curl -X POST http://localhost:8080/reason \
  -H "Content-Type: application/json" \
  -d '{"kb_id": "rbac", "delta_knowledge": "human(plato)", "query": "mortal($who)"}'

curl -X POST http://localhost:8080/list-kbs \
  -H "Content-Type: application/json" \
  -d '{}'

curl -X POST http://localhost:8080/unregister-kb \
  -H "Content-Type: application/json" \
  -d '{"kb_id": "rbac"}'

Docker

The Docker image bundles SWI-Prolog + Python, so no local prerequisites are needed. Base image: swipl:stable (Debian Bookworm).

Two modes via docker-compose:

bash

# MCP stdio — pipe to a local MCP client
docker compose run --rm euclid-mcp

# HTTP API — expose REST endpoints on port 8080
docker compose up euclid-api

Standalone usage:

server.ts

# Build
docker build -t euclid-mcp .

# Run HTTP API
docker run --rm -p 8080:8080 euclid-mcp \
  python3 integrations/euclid_api.py --port 8080

# Run MCP stdio (interactive)
docker run --rm -i euclid-mcp

# Quick test — reason directly from CLI
docker run --rm euclid-mcp python3 -c "
from euclid_mcp.server import reason
r = reason(knowledge='human(socrates)\nmortal(\$x) IF human(\$x)\n? mortal(\$who)')
print(r.solutions[0].substitutions)
"

Docker image size: ~370 MB (SWI-Prolog + Python 3.11 + dependencies).

Native-only (slim): a smaller image with the pure-Python Euclid-IR engine and no SWI-Prolog (EUCLID_BACKEND=native). Best for containers with limited space or as the default for small knowledge bases.

server.ts

# Build
docker build -f Dockerfile.native -t euclid-mcp-native .

# Run MCP stdio (interactive)
docker compose run --rm euclid-mcp-native

# Run HTTP API
docker run --rm -p 8080:8080 euclid-mcp-native \
  python3 integrations/euclid_api.py --port 8080

# Quick test — reason directly from CLI
docker run --rm euclid-mcp-native python3 -c "
from euclid_mcp.server import reason
r = reason(knowledge='human(socrates)\nmortal(\$x) IF human(\$x)\n? mortal(\$who)')
print(r.solutions[0].substitutions)
"

Base image: python:3.12-slim.

CLI pipeline

bash

echo '{"knowledge": "red(apple)\\n? red($x)"}' | python3 integrations/euclid_cli.py

See integrations/README.md for full details.

Scalability

Euclid-MCP engine is persistent: a single long-lived SWI-Prolog process per server instance, reloaded per request over a JSON-lines pipe instead of booting Prolog for every call. A single instance handles one request at a time. Requests stay stateless: each one brings its own knowledge base (or uses the preloaded one), so instances share nothing.

This makes Euclid-MCP horizontally scalable:

HTTP API — run any number of instances behind a load balancer (nginx, a Kubernetes Service, …). No session affinity needed: any instance can serve any request.
MCP stdio — each MCP client spawns its own instance by design, giving natural isolation and parallelism across clients.
Resource footprint — one swipl process per instance (~tens of MB) instead of one short-lived process per request, so a single instance serves many requests cheaply.

Reference production architecture — load balancing, resource limits, security hardening, and monitoring for a replica battery behind HAProxy: docs/PRODUCTION.md.

Development

Requirements: Python ≥ 3.10, SWI-Prolog.

bash

# Install in editable mode with dev dependencies
python3 -m venv .venv && source .venv/bin/activate
pip install -e ".[dev]"

# Lint
ruff check .

# Type check
mypy euclid_mcp integrations

# Tests with coverage
pytest --cov=euclid_mcp --cov=integrations

The CI workflow (.github/workflows/ci.yml) runs these same checks on push and pull request, across Python 3.10–3.14.

Logging & tracing

Every tool call is logged with its name, elapsed time, and outcome. Enable structured logs by setting EUCLID_LOG_LEVEL (one of DEBUG, INFO, WARNING, ERROR, CRITICAL) — e.g. EUCLID_LOG_LEVEL=INFO. Without the variable, only warnings and errors are emitted.

The HTTP API also supports request tracing: send an X-Request-Id header and it is echoed back on the response and included in the access logs.

Monitoring & metrics

The HTTP API exposes Prometheus metrics on GET /metrics (open, read-only, never carries KB content): per-tool call/error counters and latency histograms, engine requests/restarts/timeouts, HTTP traffic, solutions returned, auth failures and process uptime — always on, zero dependencies (euclid_mcp/metrics.py). GET /health is a deep check that pings the engine and reports its workspace stats (503 only when a wedged engine exists).

Terminal

curl -s localhost:8080/metrics

For a full stack (Prometheus + Grafana + cAdvisor, dashboard and alert rules included): monitoring/README.md.

What is Prolog?

Prolog (from PROgrammation en LOGique) is a declarative logic programming language: instead of telling the machine how to compute an answer, you state facts and rules and let it find what follows from them, using unification and backtracking. Born in the early 1970s, it remains one of the most battle-tested tools for symbolic reasoning.

SWI-Prolog

Euclid-MCP uses SWI-Prolog as its inference engine. SWI-Prolog is a mature open-source implementation — continuously developed and freely available since 1987 — widely used in industry, academia, and research. You write your rules in Euclid-IR; the translator compiles them to Prolog, and SWI-Prolog performs the deduction and produces the proof trees that make every Euclid-MCP answer verifiable.

How is Euclid?

Euclid was an ancient Greek mathematician. Living and teaching in Alexandria, he built the foundations of geometry and number theory using rigorous logical proofs.

Euclid-MCP is not:

an LLM
a knowledge base
a vector database
an agent framework
a planner

Euclid-MCP is a deterministic inference engine that can be used by any of them.
Euclid-MCP allows deterministic and explainable replies from small LLMs on Edge hardware too.

License

Apache 2.0

Euclid-MCP

How it works

Knowledge Base

Intermediate Language

Euclid-IR Syntax Reference

Arithmetic Comparisons

Multi-line Rules

Conjunctions in Queries

Why External Inference?

Tools

reason

explain

diagnose

what_if

check_kb

KB identity in results

KB Preload

Named KBs (kb_id + delta_knowledge)

Installation

pip

From source

Docker

Usage

Via MCP (OpenCode, Claude, etc.)

Via Python

Via CLI

Example output

Diagnose output

What-if output

Explain output

Use cases

Real-world examples

Integrations

OpenCode

n8n / Zapier / Make

Docker

CLI pipeline

Scalability

Development

Logging & tracing

Monitoring & metrics

What is Prolog?

How is Euclid?

License

`reason`

`explain`

`diagnose`

`what_if`

`check_kb`

Named KBs (`kb_id` + `delta_knowledge`)