Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, email [email protected] and we’ll put it right.

io.github.tosin2013/mcp-adr-analysis-server

NPM · MCP-ADR-ANALYSIS-SERVER · SCANNED AUG 3

AI-powered MCP server for analyzing Architectural Decision Records (ADRs).

+24 this week 77 Trust /100
Trust breakdown (6 categories)

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score →

Supply Chain Security88
  • No malware found by supply-chain analysis.Pass
  • Only part of the dependency tree could be resolved (149 of 150), so this covers what we could see, not the whole tree.Partial
  • No install/post-install scripts declared.Pass
  • Only part of the dependency tree could be resolved (149 of 150), so this covers what we could see, not the whole tree. View diagnostics → Partial
Provenance & Transparency97
  • Source repository is publicly reachable at the declared URL. View diagnostics → Pass
  • Cryptographically verified build provenance (signed, bound to tosin2013/mcp-adr-analysis-server). View diagnostics → Pass
  • Clear OSI-approved license (MIT).Pass
  • Actively maintained (last published 55 days ago).Pass
  • Disclosure check failed: no security disclosure policy was found in the source repository. See how to fix → Fail
Schema Quality & AI Usability63
  • 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
  • AI-judged instruction clarity (poor).Fail
  • Context-footprint check failed: tool/resource definitions use about 10378 tokens (~102/item across 101 items; 75 tools + 26 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management23
  • Stability observed for 7 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Install

Add this component to your MCP client. Where a client-specific snippet is available, pick your client below and copy it straight into your config; otherwise use the connection detail shown.

npm · mcp-adr-analysis-server

# add to Claude Code
claude mcp add tosin2013-mcp-adr-analysis-server -- npx -y mcp-adr-analysis-server
# add to Codex CLI
codex mcp add tosin2013-mcp-adr-analysis-server -- npx -y mcp-adr-analysis-server
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "tosin2013-mcp-adr-analysis-server": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "mcp-adr-analysis-server"
      ],
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add tosin2013-mcp-adr-analysis-server --command npx --arg -y --arg mcp-adr-analysis-server
# ~/.hermes/config.yaml
mcp_servers:
  tosin2013-mcp-adr-analysis-server:
    command: "npx"
    args: ["-y", "mcp-adr-analysis-server"]
// mcp.json
{
  "mcpServers": {
    "tosin2013-mcp-adr-analysis-server": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-adr-analysis-server"
      ]
    }
  }
}
Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 3 Aug 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 20 to 23. That category is still filling its 30-day observation window: 6 days of observed history at the previous scan, 7 at this one. The score rises as the window fills, whether or not the server changes.

  • 2 Aug 26 +50
    • Install scripts: unverified → pass security
    • Provenance: unverified → pass security
    • Known CVEs: unverified → partial security
    • Malware scan: unverified → pass security
    • The attested source repository moved: tosin2013/mcp-adr-analysis-server security
    • License: unverified → pass functional
    • Dependency health: unverified → partial functional
    • Stability: unverified → 0.20 functional
    • Maintenance: unverified → pass functional
    • MCP protocol: unverified → pass functional
    • Schema quality: unverified → poor functional
    • Licence: MIT functional
  • 31 Jul 26 −27
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 30 Jul 26 +28
    • Dependency health: partial → unverified functional
    • Schema quality: unverified → 100 functional
    • Tool coverage: unverified → 100 functional
  • 28 Jul 26 −28
    • Tool coverage: 100 → unverified functional
    • Schema quality: 100 → unverified functional
    • Dependency health: unverified → partial functional
  • 27 Jul 26 53

    First indexed and scored.

Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 3 Aug 2026 · Analysed npm/[email protected]

Provenance verified

Ecosystem: npm · Outcome: verified

Reason: verified

Source repo:
tosin2013/mcp-adr-analysis-server
Certificate issuer:
https://token.actions.githubusercontent.com
Certificate SAN:
https://github.com/tosin2013/mcp-adr-analysis-server/.github/workflows/publish.yml@refs/tags/v2.6.9
Rekor log index:
1756529168
Predicate type:
https://slsa.dev/provenance/v1
Subject digest:
sha512:3344b60c153fff19c51caaa511897f829e1e8df434a1759bbf9c883f0774c0127333bb4460626b296df09d3b97b940fa27a2d172278ab81ee273db58a
Discovery method:
attestation_endpoint
Dependencies 149 packages

149 packages in the resolved dependency tree · 143 deprecated · 43 stale.

The dependency tree was only partially resolved, so these counts may be incomplete.

MCP tools — 75 exposed · ~9,627 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability.

Tool Tokens
memory_loading ~115

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.

NameTypeReqDescription
actionstringMemory operation to perform
entityIdstringEntity ID for get_entity and find_related actions
forceReloadbooleanForce reload of ADRs (load_adrs action)
maxDepthnumberMaximum depth for relationship traversal (find_related action)
queryobjectQuery parameters for entity search

No output schema declared.

No examples provided.

perform_research ~102

Perform research using cascading sources: project files → knowledge graph → environment resources → web search (fallback)

NameTypeReqDescription
adrDirectorystringDirectory containing ADR files
confidenceThresholdnumberMinimum confidence threshold (0-1) before suggesting web search
performWebSearchbooleanEnable web search recommendations when confidence is low
projectPathstringPath to project directory
questionstringyesThe research question to answer

No output schema declared.

No examples provided.

query_conversation_history ~87

Phase 3: Search and retrieve conversation sessions based on filters

NameTypeReqDescription
dateRangeobjectFilter by date range
keywordstringSearch keyword in conversation turns
limitnumberMaximum number of sessions to return
projectPathstringFilter by project path
toolsUsedarrayFilter by tools used in the session

No output schema declared.

No examples provided.

read_directory ~47

List files and folders in a directory. Use this to explore the file structure within accessible roots.

NameTypeReqDescription
pathstringyesDirectory path to list (relative to project root or absolute within roots)

No output schema declared.

No examples provided.

read_file ~46

Read contents of a file

NameTypeReqDescription
filePathstringPath to the file to read
pathstringPath to the file to read (alias for filePath)

No output schema declared.

No examples provided.

release_tracking ~397

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.

NameTypeReqDescription
compareFromstringStarting version for comparison
compareTostringEnding version for comparison
createGithubReleasebooleanCreate a GitHub Release (requires gh CLI)
formatstringChangelog output format
groupByAdrbooleanGroup changelog entries by ADR
includeAdrLinksbooleanInclude ADR references in changelog
includeCommitHashesbooleanInclude commit hashes in output
includeReadinessbooleanInclude release readiness score
includeTimelinebooleanInclude mermaid timeline diagram
localOnlybooleanFor create_milestone: persist locally instead of calling gh CLI. Useful when gh auth is unavailable.
milestoneDescriptionstringGitHub milestone description
milestoneDueDatestringMilestone due date (YYYY-MM-DD)
milestoneTitlestringGitHub milestone title (for create_milestone)
operationstringyesOperation to perform
projectPathstringProject root path (defaults to current working directory)
releasePlanPathstringPath to RELEASE_PLAN.md (relative to projectPath).
syncGithubMilestonesbooleanSync milestones to GitHub (requires gh CLI)
updateTodobooleanUpdate TODO.md with milestone status
versionstringRelease version to track (e.g., v2.3.0)
writeReleasePlanbooleanFor create_milestone/push_local_milestones: also render local milestones into RELEASE_PLAN.md (bounded section).
writeToFilebooleanWrite CHANGELOG.md to repo

No output schema declared.

No examples provided.

request_action_confirmation ~55

Request confirmation before applying research-based changes

NameTypeReqDescription
actionstringyesDescription of the action to be performed
detailsstringyesDetailed information about the action
impactstringImpact level of the action

No output schema declared.

No examples provided.

review_existing_adrs ~159

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.

NameTypeReqDescription
adrDirectorystringDirectory containing ADR files
analysisDepthstringDepth of analysis to perform
conversationContextobjectRich context from the calling LLM about user goals and discussion history
generateUpdatePlanbooleanGenerate action plan for updating non-compliant ADRs
includeTreeSitterbooleanUse tree-sitter for enhanced code analysis
projectPathstringPath to the project directory
specificAdrstringSpecific ADR filename or title to review (optional)

No output schema declared.

No examples provided.

search_codebase ~151

Atomic tool for searching codebase files based on query patterns. Returns raw file matches with relevance scores. Extracted from ResearchOrchestrator per ADR-018.

NameTypeReqDescription
enableTreeSitterbooleanUse tree-sitter for enhanced analysis
includeContentbooleanInclude file content in results
maxFilesnumberMaximum files to return
projectPathstringPath to project root
querystringyesSearch query (e.g., "Docker configuration", "authentication")
relevanceThresholdnumberMinimum relevance threshold (0-1)
scopearrayOptional file scope patterns (e.g., ["src/**", "config/**"])

No output schema declared.

No examples provided.

search_tools ~147

Search and discover available tools by category, keyword, or capability. Use this to find the right tool for a task without loading all tool schemas. Returns lightweight tool metadata by default; use includeSchema:true for full schemas.

NameTypeReqDescription
categorystringFilter tools by category
cemcpOnlybooleanOnly return tools with CE-MCP directive support (more token-efficient)
complexitystringFilter by tool complexity level
includeSchemabooleanInclude full input schemas in response (increases token count)
limitnumberMaximum number of tools to return
querystringSearch query to match tool names, descriptions, and keywords

No output schema declared.

No examples provided.

set_project_path ~96

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.

NameTypeReqDescription
pathstringyesAbsolute path to the project directory. Must be an existing directory.
validatePathbooleanWhether to validate that the path exists and is a directory (default: true)

No output schema declared.

No examples provided.

smart_git_push ~166

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.

NameTypeReqDescription
branchstringTarget branch for push (optional, uses current branch if not specified)
dryRunbooleanShow what would be pushed without actually pushing
forceUnsafebooleanOverride security blocks and test failures (DANGEROUS)
messagestringCommit message (optional, commits staged files if provided)
projectPathstringPath to project directory (defaults to current working directory)
skipSecuritybooleanSkip security scanning (NOT RECOMMENDED)
testResultsobjectTest results from AI-executed tests (required for proper deployment tracking)

No output schema declared.

No examples provided.

smart_score ~343

Central coordination for project health scoring system - recalculate, sync, diagnose, optimize, and reset scores across all MCP tools

NameTypeReqDescription
analysisModestringMethod for weight optimization (for optimize_weights operation)
checkDataFreshnessbooleanValidate data freshness across tools (for diagnose_scores operation)
componentstringScore component to reset (for reset_scores operation)
componentsarrayScore components to recalculate (for recalculate_scores operation)
customWeightsobjectCustom weight overrides (for optimize_weights operation)
forceUpdatebooleanForce update even if data is fresh
includeHistorybooleanInclude score history analysis (for diagnose_scores operation)
intentIdstringIntent ID to get score trends for (for get_intent_scores operation)
operationstringyesSmart scoring operation to perform
preserveHistorybooleanPreserve score history in backup (for reset_scores operation)
previewOnlybooleanPreview changes without applying (for optimize_weights operation)
projectPathstringyesPath to project directory
rebalanceWeightsbooleanRecalculate optimal scoring weights (for sync_scores operation)
recalculateAfterResetbooleanImmediately recalculate after reset (for reset_scores operation)
suggestImprovementsbooleanProvide score improvement suggestions (for diagnose_scores operation)
todoPathstringPath to TODO.md file (for sync_scores operation)
triggerToolsarrayTools to trigger for fresh data (for sync_scores operation)
updateSourcesbooleanTrigger source tool updates before recalculating

No output schema declared.

No examples provided.

suggest_adrs ~226

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.

NameTypeReqDescription
afterCodestringCode after changes (for code_changes analysis)
analysisTypestringType of analysis to perform
beforeCodestringCode before changes (for code_changes analysis)
changeDescriptionstringDescription of the changes (for code_changes analysis)
commitMessagesarrayRelated commit messages (for code_changes analysis)
conversationContextobjectRich context from the calling LLM about user goals and discussion history
enhancedModebooleanEnable advanced prompting features (Knowledge Generation + Reflexion)
existingAdrsarrayList of existing ADR titles to avoid duplication
knowledgeEnhancementbooleanEnable Knowledge Generation for domain-specific insights
learningEnabledbooleanEnable Reflexion learning from past experiences
projectPathstringPath to the project directory

No output schema declared.

No examples provided.

sync_to_aggregator ~173

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.

NameTypeReqDescription
adr_pathsarraySpecific ADR paths to sync (syncs all if not provided)
full_syncbooleanReplace all ADRs instead of incremental sync
include_code_linksbooleanInclude AST-based code links (Pro+ tier)
include_diagramsbooleanInclude Mermaid diagrams (Pro+ tier)
include_metadatabooleanInclude analysis metadata in sync
include_security_scanbooleanInclude security scan results
include_timelinebooleanInclude timeline/staleness data
projectPathstringProject path (defaults to PROJECT_PATH)

No output schema declared.

No examples provided.

tool_chain_orchestrator ~119

AI-powered dynamic tool sequencing - intelligently analyze user requests and generate structured tool execution plans

NameTypeReqDescription
allowParallelbooleanAllow parallel execution of independent steps
availableToolsarrayList of available MCP tools to orchestrate
contextHintsarrayAdditional context hints for better plan generation
executionModestringOrchestration mode
maxStepsnumberMaximum number of steps in the execution plan
userRequeststringyesUser request to analyze and create tool execution plan for

No output schema declared.

No examples provided.

troubleshoot_guided_workflow ~202

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

NameTypeReqDescription
adrDirectorystringADR directory path
conversationContextobjectRich context from the calling LLM about user goals and discussion history
enableAdrSuggestionbooleanEnable automatic ADR suggestion based on recurring failures
enableMemoryIntegrationbooleanEnable memory entity storage for troubleshooting session tracking and pattern recognition
enablePatternRecognitionbooleanEnable automatic pattern recognition and failure classification
enableResearchGenerationbooleanEnable automatic research question generation for persistent problems
failureobjectStructured failure information (required for analyze_failure and generate_test_plan)
operationstringyesType of troubleshooting operation
projectPathstringPath to project directory (optional)
todoPathstringPath to TODO.md file

No output schema declared.

No examples provided.

update_implementation_status ~72

Update the implementation status of synced ADRs directly from the IDE. Supports statuses: not_started, in_progress, implemented, deprecated, blocked. Requires Pro+ tier.

NameTypeReqDescription
projectPathstringProject path (defaults to PROJECT_PATH)
updatesarrayyesArray of ADR status updates to apply

No output schema declared.

No examples provided.

update_knowledge ~157

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).

NameTypeReqDescription
entitystringEntity ID (for add_entity/remove_entity operations)
entityTypestringType of entity (required for add_entity operation)
metadataobjectAdditional metadata for the entity or relationship
operationstringyesType of operation to perform on the knowledge graph
relationshipstringRelationship type (for add_relationship/remove_relationship)
sourcestringSource node ID (for relationship operations)
targetstringTarget node ID (for relationship operations)

No output schema declared.

No examples provided.

validate_adr ~115

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.

NameTypeReqDescription
adrDirectorystringDirectory containing ADR files
adrPathstringyesPath to the ADR file to validate (relative or absolute)
confidenceThresholdnumberMinimum research confidence threshold (0-1)
includeEnvironmentCheckbooleanInclude live environment verification in validation
projectPathstringPath to the project directory

No output schema declared.

No examples provided.

validate_adr_compliance ~75

Validate ADR compliance against implementation via ADR Aggregator. Checks that code actually implements documented decisions. Requires Pro+ tier.

NameTypeReqDescription
adr_pathsarraySpecific ADR paths to validate
projectPathstringProject path (defaults to PROJECT_PATH)
validation_typestringType of validation to perform

No output schema declared.

No examples provided.

validate_all_adrs ~79

Validate all ADRs in a directory against actual infrastructure reality

NameTypeReqDescription
adrDirectorystringDirectory containing ADR files
includeEnvironmentCheckbooleanInclude live environment verification in validation
minConfidencenumberMinimum research confidence for validation (0-1)
projectPathstringPath to the project directory

No output schema declared.

No examples provided.

validate_content_masking ~41

Validate that content masking was applied correctly

NameTypeReqDescription
maskedContentstringyesContent after masking
originalContentstringyesOriginal content before masking

No output schema declared.

No examples provided.

validate_rules ~97

Validate code against architectural rules

NameTypeReqDescription
fileContentstringContent to validate (alternative to filePath)
fileNamestringName of file being validated (when using fileContent)
filePathstringPath to file to validate
reportFormatstringFormat for validation report
rulesarrayyesRules to validate against
validationTypestringType of validation to perform

No output schema declared.

No examples provided.

write_file ~40

Write content to a file

NameTypeReqDescription
contentstringyesContent to write to the file
pathstringyesPath to the file to write

No output schema declared.

No examples provided.