Enhanced MCP server for Limitless Pendant with advanced conversation analysis, meeting detection, action item extraction, and comprehensive
Free
Nothing to run from here
Adr Analysis is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
Open Installation—
p95 latency
—
call success
local
runs on your machine
—
calls last 7d
What it does
MCP server for analyzing Architectural Decision Records and project architecture
Quickstart
# 1 — run it from where its publisher ships it
npx -y mcp-adr-analysis-server
# 2 — ask your agent something
> MCP server for analyzing Architectural Decision Records and project architecture
Adr Analysis is free: there is no plan to choose, no cap to set and nothing that can bill you.
Publishernot claimed
TOAll 2 servers
tosin20132 servers
2 categories
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. This one runs on your machine: your client starts Adr Analysis as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. It is scanned, signed and pinned to the version you choose — read the surface before you approve it.
Claude Codedeclared by this listing
This is a public server: you run it yourself and this marketplace is not in the path. Claude Code registers it in one command.
claude mcp add adr-analysis-mcp -- npx -y mcp-adr-analysis-serverReconnect, or start a new session, and the tools appear in the model’s tool list.
Free to install, and it runs from its publisher’s own package: no account, no key, no card.
What it asks of you
Nothing is required, but it can take PROJECT_PATH, OPENROUTER_API_KEY, EXECUTION_MODE, ADR_DIRECTORY if you want to set them.
What it writes
One config entry your client uses to start the process locally. A local server runs with your file system and your network, which is why it is priced without metering.
What you approve
72 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
MCP server for analyzing Architectural Decision Records and project architecture
Takes no parameters.
Example callreturns →
Comprehensive recursive project ecosystem analysis with advanced prompting techniques (Knowledge Generation + Reflexion)
Takes no parameters.
Example callreturns →
Get detailed architectural context for specific files or the entire project, automatically sets up ADR infrastructure if missing, and provides outcome-focused workflow for project success
Takes no parameters.
Example callreturns →
Generate Architectural Decision Records from a Product Requirements Document with advanced prompting techniques (APE + Knowledge Generation)
Takes no parameters.
Example callreturns →
Compare TODO.md progress against ADRs and current environment to validate implementation status
Takes no parameters.
Example callreturns →
Analyze content for sensitive information using AI-powered detection with optional memory integration for security pattern learning
Takes no parameters.
Example callreturns →
Generate masking instructions for detected sensitive content
Takes no parameters.
Example callreturns →
Configure custom sensitive patterns for a project
Takes no parameters.
Example callreturns →
Apply basic content masking (fallback when AI is not available)
Takes no parameters.
Example callreturns →
Validate that content masking was applied correctly
Takes no parameters.
Example callreturns →
Manage MCP resource cache (clear, stats, cleanup)
Takes no parameters.
Example callreturns →
Configure content masking for all MCP outputs
Takes no parameters.
Example callreturns →
Suggest architectural decisions with advanced prompting techniques (Knowledge Generation + Reflexion). TIP: Read @.mcp-server-context.md first for project history, patterns, and previous ADRs to ensure consistency.
Takes no parameters.
Example callreturns →
Generate a complete ADR from decision data. TIP: Reference @.mcp-server-context.md to align with existing architectural patterns and decisions.
Takes no parameters.
Example callreturns →
Discover and catalog existing ADRs in the project
Takes no parameters.
Example callreturns →
Analyze ADR timeline with smart time tracking, adaptive thresholds, and actionable recommendations. Auto-detects project context (startup/growth/mature) and generates prioritized work queue based on staleness, implementation lag, and technical debt.
Takes no parameters.
Example callreturns →
Review existing ADRs against actual code implementation with cloud/DevOps expertise. TIP: After review, call get_server_context to update @.mcp-server-context.md with findings.
Takes no parameters.
Example callreturns →
Validate an existing ADR against actual infrastructure reality using research-driven analysis. TIP: Compare findings against patterns in @.mcp-server-context.md for consistency checks.
Takes no parameters.
Example callreturns →
Validate all ADRs in a directory against actual infrastructure reality
Takes no parameters.
Example callreturns →
Incorporate research findings into architectural decisions
Takes no parameters.
Example callreturns →
Create a research template file for documenting findings
Takes no parameters.
Example callreturns →
Request confirmation before applying research-based changes
Takes no parameters.
Example callreturns →
Generate architectural rules from ADRs and code patterns
Takes no parameters.
Example callreturns →
Validate code against architectural rules
Takes no parameters.
Example callreturns →
Create machine-readable rule set in JSON/YAML format
Takes no parameters.
Example callreturns →
Analyze environment context and provide optimization recommendations with optional memory integration for environment snapshot tracking
Takes no parameters.
Example callreturns →
Generate context-aware research questions and create research tracking system
Takes no parameters.
Example callreturns →
Perform research using cascading sources: project files → knowledge graph → environment resources → web search (fallback)
Takes no parameters.
Example callreturns →
Atomic tool for searching codebase files based on query patterns. Returns raw file matches with relevance scores. Extracted from ResearchOrchestrator per ADR-018.
Takes no parameters.
Example callreturns →
LLM-managed web search using Firecrawl for cross-platform support
Takes no parameters.
Example callreturns →
LLM-managed cloud provider operations with research-driven approach
Takes no parameters.
Example callreturns →
LLM-managed database operations with research-driven approach
Takes no parameters.
Example callreturns →
Analyze deployment progress and verify completion with outcome rules
Takes no parameters.
Example callreturns →
Check AI execution configuration and status for debugging prompt-only mode issues
Takes no parameters.
Example callreturns →
Get intelligent workflow guidance and tool recommendations based on your goals and project context to achieve expected outcomes efficiently
Takes no parameters.
Example callreturns →
Get comprehensive development guidance that translates architectural decisions and workflow recommendations into specific coding tasks, implementation patterns, and development roadmap
Takes no parameters.
Example callreturns →
List available file system roots that can be accessed. Use this to discover what directories are available before reading files.
Takes no parameters.
Example callreturns →
List files and folders in a directory. Use this to explore the file structure within accessible roots.
Takes no parameters.
Example callreturns →
Read contents of a file
Takes no parameters.
Example callreturns →
Write content to a file
Takes no parameters.
Example callreturns →
List contents of a directory
Takes no parameters.
Example callreturns →
Generate deployment guidance and instructions from ADRs with environment-specific configurations
Takes no parameters.
Example callreturns →
AI-driven security-focused git push with credential detection, file filtering, and deployment metrics tracking. Tests should be run by calling AI and results provided.
Takes no parameters.
Example callreturns →
Comprehensive deployment readiness validation with test failure tracking, deployment history analysis, and hard blocking for unsafe deployments. Integrates with smart_git_push for deployment gating.
Takes no parameters.
Example callreturns →
Track releases mapped to ADR decisions. Generates changelogs, manages milestones, compares releases, and assesses release readiness. Supports greenfield and brownfield projects. Writes CHANGELOG.md, creates GitHub Releases and Milestones.
Takes no parameters.
Example callreturns →
Structured failure analysis and test plan generation with memory integration for troubleshooting session tracking and intelligent ADR/research suggestion capabilities - provide JSON failure info to get specific test commands
Takes no parameters.
Example callreturns →
Central coordination for project health scoring system - recalculate, sync, diagnose, optimize, and reset scores across all MCP tools
Takes no parameters.
Example callreturns →
Enhanced project planning and workflow management tool - phase-based project management, team resource allocation, progress tracking, risk analysis, and executive reporting
Takes no parameters.
Example callreturns →
Interactive guided ADR planning and creation tool - walks users through structured decision-making process with research integration, option evaluation, and automatic ADR generation. TIP: Start by reading @.mcp-server-context.md to understand project context and previous decisions.
Takes no parameters.
Example callreturns →
Advanced memory loading tool for the memory-centric architecture. Query, explore, and manage memory entities and relationships. Load ADRs into memory system and perform intelligent queries.
Takes no parameters.
Example callreturns →
Retrieve full analysis content from tiered responses. Expand entire analysis or specific sections stored in memory. Use this when a tool returns a summary with an expandable ID.
Takes no parameters.
Example callreturns →
AI-powered dynamic tool sequencing - intelligently analyze user requests and generate structured tool execution plans
Takes no parameters.
Example callreturns →
Phase 3: Retrieve and expand stored content from a tiered response using its expandable ID
Takes no parameters.
Example callreturns →
Phase 3: Search and retrieve conversation sessions based on filters
Takes no parameters.
Example callreturns →
Phase 3: Get current conversation context snapshot for resumption or analysis
Takes no parameters.
Example callreturns →
Phase 3: Get statistics about stored conversation memory
Takes no parameters.
Example callreturns →
ADR-018: Simple CRUD operations for knowledge graph. Add/remove entities (intents, ADRs, tools, code) and relationships. Use knowledge://graph resource to read current state (zero token cost).
Takes no parameters.
Example callreturns →
Generate a comprehensive context file showing the server
Takes no parameters.
Example callreturns →
Get the current date and time in various formats. Useful for timestamping ADRs, research documents, and other architectural artifacts. Returns ISO 8601, human-readable, and ADR-specific date formats.
Takes no parameters.
Example callreturns →
Dynamically set the active project path for the current session. Call this at the start of a session to switch between projects without restarting the server or modifying environment variables. All subsequent tool calls will use this path as the default.
Takes no parameters.
Example callreturns →
Load a specific prompt or prompt section on-demand. Part of CE-MCP lazy loading system that reduces token usage by ~96% by loading prompts only when needed. Use this to retrieve prompt templates for ADR generation, analysis, deployment, and other operations.
Takes no parameters.
Example callreturns →
Sync ADRs to ADR Aggregator platform (https://adraggregator.com) for centralized tracking, visualization, and team collaboration. Supports incremental and full sync modes with optional metadata.
Takes no parameters.
Example callreturns →
Fetch ADR context from ADR Aggregator including summaries, diagrams, timeline data, and code links. Useful for getting a consolidated view of architectural decisions.
Takes no parameters.
Example callreturns →
Get ADR staleness report from ADR Aggregator with review compliance metrics. Identifies stale ADRs that need attention and provides governance insights.
Takes no parameters.
Example callreturns →
Get domain-specific ADR templates and anti-patterns from ADR Aggregator. Includes best practices for web applications, microservices, APIs, and more. No authentication required.
Takes no parameters.
Example callreturns →
Get Mermaid diagrams for ADRs from ADR Aggregator. Includes workflow, relationship, and impact diagrams. Requires Pro+ tier.
Takes no parameters.
Example callreturns →
Validate ADR compliance against implementation via ADR Aggregator. Checks that code actually implements documented decisions. Requires Pro+ tier.
Takes no parameters.
Example callreturns →
Get cross-repository knowledge graph from ADR Aggregator with analytics and insights. Visualize ADR relationships across repositories. Requires Team tier.
Takes no parameters.
Example callreturns →
Update the implementation status of synced ADRs directly from the IDE. Supports statuses: not_started, in_progress, implemented, deprecated, blocked. Requires Pro+ tier.
Takes no parameters.
Example callreturns →
Get ADR priorities for roadmap and backlog planning from ADR Aggregator. Returns prioritized ADRs with scores, dependencies, blockers, implementation status, and gap counts.
Takes no parameters.
Example callreturns →
Scan local codebase and compare with ADRs to detect bi-directional gaps. Finds: (1) ADR-to-code gaps: file references in ADRs that do not exist, (2) Code-to-ADR gaps: technologies in package.json and architectural patterns without ADR coverage. Reports gaps to ADR Aggregator for tracking.
Takes no parameters.
Example callreturns →
Get current code gaps from ADR Aggregator. Returns gaps with their status (open, dismissed, resolved) for tracking and management.
Takes no parameters.
Example callreturns →
Freeyour plan
$0 forever
- Every tool, no call limit
- No card, no account needed
- Source published under a licence you can read
- Runs on your machine — nothing of it reaches our gateway
- Nothing to cap, because nothing bills
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable. Adr Analysis costs nothing to install and nothing to call, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: $8.42
$16.58 left
CTrust score 79 / 100
Release 2.6.14 · scanned 25 Aug 2026
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
Threat score89
Client score79
Findings6 threat · 16 capability
Capabilitycritical
Coveragesource
Verificationsource
Surface digestbcc5216b688793425e4e2ef9b1c2ed06546c742854b4a5e2b2c43c54947e112b
Score vectorthreat 89 → client 79
| Term | Level | What it prices | Points |
|---|---|---|---|
| −6.3 | |||
| −3.15 | |||
| −1.58 | |||
| capability-exposure | critical | capability blast radius (critical) — client exposure if the model is manipulated | −10 |
| verification-discount | source | publisher verification (provenance) — cryptographic build provenance ties the artifact to its source | −0 |
| coverage-honesty | source | inspection depth (source) — how much of the target the scan could see | −0 |
score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
Tool surfaceread
Implementation sourceread
Package metadataread
Live transportnot available
Tools were statically extracted from the published source (101 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. critical is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| mcp-adr-analysis-server | no tags | |
| analyze_project_ecosystem | no tags | |
| get_architectural_context | no tags | |
| generate_adrs_from_prd | no tags | |
| compare_adr_progress | no tags | |
| analyze_content_security | no tags | |
| generate_content_masking | no tags | |
| configure_custom_patterns | no tags | |
| apply_basic_content_masking | no tags | |
| validate_content_masking | no tags | |
| manage_cache | no tags | |
| configure_output_masking | no tags | |
| suggest_adrs | no tags | |
| generate_adr_from_decision | no tags | |
| generate_adr_bootstrap | no tags | |
| bootstrap_validation_loop | no tags | |
| discover_existing_adrs | no tags | |
| analyze_adr_timeline | no tags | |
| review_existing_adrs | no tags | |
| validate_adr | no tags | |
| validate_all_adrs | no tags | |
| incorporate_research | no tags | |
| create_research_template | no tags | |
| request_action_confirmation | no tags | |
| generate_rules | no tags | |
| validate_rules | no tags | |
| create_rule_set | no tags | |
| analyze_environment | no tags | |
| generate_research_questions | no tags | |
| perform_research | untrusted-input | |
| search_codebase | no tags | |
| llm_web_search | untrusted-input | |
| llm_cloud_management | no tags | |
| llm_database_management | no tags | |
| analyze_deployment_progress | no tags | |
| check_ai_execution_status | no tags | |
| get_workflow_guidance | no tags | |
| get_development_guidance | no tags | |
| list_roots | no tags | |
| read_directory | sensitive-source | |
| read_file | sensitive-source | |
| write_file | file-write | |
| list_directory | no tags | |
| generate_deployment_guidance | no tags | |
| smart_git_push | no tags | |
| deployment_readiness | no tags | |
| release_tracking | no tags | |
| generate_adr_todo | no tags | |
| troubleshoot_guided_workflow | no tags | |
| smart_score | no tags | |
| mcp_planning | no tags | |
| interactive_adr_planning | no tags | |
| memory_loading | no tags | |
| expand_analysis_section | no tags | |
| tool_chain_orchestrator | no tags | |
| expand_memory | no tags | |
| query_conversation_history | no tags | |
| get_conversation_snapshot | no tags | |
| get_memory_stats | no tags | |
| update_knowledge | no tags | |
| get_server_context | no tags | |
| get_current_datetime | no tags | |
| set_project_path | no tags | |
| load_prompt | no tags | |
| sync_to_aggregator | no tags | |
| get_adr_context | untrusted-input | |
| get_staleness_report | no tags | |
| get_adr_templates | no tags | |
| get_adr_diagrams | no tags | |
| validate_adr_compliance | no tags | |
| get_knowledge_graph | no tags | |
| update_implementation_status | no tags | |
| get_adr_priorities | no tags | |
| analyze_gaps | no tags | |
| get_gaps | no tags | |
| Architectural Knowledge Graph | no tags | |
| Analysis Report | no tags | |
| ADR List | no tags | |
| Todo List | no tags | |
| Research Index | no tags | |
| Rule Catalog | no tags | |
| Rule Generation | no tags | |
| Project Status | no tags | |
| ADR by ID | no tags | |
| Research by Topic | no tags | |
| Todo by Task ID | no tags | |
| Rule by ID | no tags | |
| Deployment Status | no tags | |
| Environment Analysis | no tags | |
| Memory Snapshots | no tags | |
| Project Metrics | no tags | |
| Technology by Name | no tags | |
| Pattern by Name | no tags | |
| Deployment History | no tags | |
| Release History | no tags | |
| Code Quality | no tags | |
| Validated Patterns Catalog | no tags | |
| Validated Pattern by Platform | no tags | |
| Pattern Authoritative Sources | no tags | |
| Pattern Base Code Repository | no tags | |
| Knowledge Graph | no tags |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.
Supply chain and provenance
Integrityfirst-seen
Surface digestbcc5216b68879342
Scanned2026-08-25
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
Pinned to 2.6.14 — the install command below asks for that release. A pin is part of an install, so it is kept for this visit and written down when you install.
2.6.14
undated
installedNo release note was published with this version.
—
no reviews yet
Reviews are earned
Only accounts with at least 50 real tool calls against this server in the last 90 days can post. Ratings are weighted by how much the reviewer actually uses it, and publishers can reply once per review.
Reviews are earned
Writing one takes an account with at least 50 real tool calls against Adr Analysis in the last 90 days. That is the whole gate — there is no other way to post, which is why the counts beside each review are worth reading.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes an account with 50 real tool calls against it.