Prism Coder MCP server
Session memory for coding agents: local-first recall, drift detection, on-device inference.
157 stars1.3k downloads/wk
Reviews
Write oneNobody has reviewed Prism Coder yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
Prism Coder tools (57, 3 write)
write = sends, deletes, buys or postsRead from the package source without running it. The installed server may list more.
agent_heartbeatwrite actionUpdate your heartbeat and optionally your current task.
agent_list_teamList all agents on a project with health status. Shows role, health state
agent_registerRegister this agent with the Hivemind team for a project.
api_analyticsView API usage analytics per project or system-wide.
backup_databasewrite actionCreate, list, or restore SQLite database backups.
brave_answersReturns direct AI answers grounded in Brave Search using Brave AI Grounding.
brave_local_searchSearches for local businesses and places using Brave's Local Search API.
brave_local_search_code_modePerforms a local search using Brave APIs, and then runs a custom JavaScript code string against the RAW API RESPONSE in a secure QuickJS sandbox.
brave_web_searchPerforms a web search using the Brave Search API, ideal for general queries, news, articles, and online content.
brave_web_search_code_modePerforms a web search using the Brave Search API, and then runs a custom JavaScript code string against the RAW API RESPONSE in a secure QuickJS sandbox.
code_mode_transformA universal code-mode transformer. Takes RAW TEXT or JSON output from ANY MCP tool (GitHub, Firecrawl, chrome-devtools, camoufox, codegraphcontext, videoMcp, arxiv, etc.)
configure_notificationsConfigure real-time notifications for memory events via webhook, Slack, or email.
deep_storage_purgev5.1 Deep Storage Mode: Purge high-precision float32 embedding vectors for entries
extract_entitiesExtract named entities from raw text using rule-based + optional LLM extraction.
gemini_research_paper_analysisPerforms in-depth analysis of research papers using Google's Gemini-2.0-flash model.
inference_metricsReturns local-model inference metrics — call count, local vs cloud split,
knowledge_downvoteDownvote a memory entry to decrease its importance.
knowledge_forgetSelectively forget (delete) accumulated knowledge entries.
knowledge_ingestIngest source code or documentation into the knowledge graph.
knowledge_searchSearch accumulated knowledge across all sessions by keywords, category, or free text.
knowledge_set_retentionSet an automatic data retention policy (TTL) for a project's memory.
knowledge_sync_rulesAuto-sync graduated insights (importance >= 7) into your project's IDE rules file
knowledge_upvoteUpvote a memory entry to increase its importance (graduation).
local_savingsReports what prism's local serving displaced, in TOKENS: volume handled by a
maintenance_vacuumReclaim disk space after large purge operations by running VACUUM on the local SQLite database.
memory_checkoutTime travel! Restores the project's memory to a specific past version.
memory_historyView the timeline of past memory states for this project.
onboarding_wizardInteractive setup wizard for new Prism users. Provides a step-by-step
query_memory_naturalQuery memories using natural language instead of structured tool syntax.
scholar_researchTriggers an autonomous research pipeline on a specific topic.
session_abort_pipelineAbort a running Dark Factory pipeline. The pipeline will be marked as ABORTED
session_backfill_embeddingsRepair ledger entries that are missing vector embeddings.
session_backfill_linksRetroactively create graph edges (memory links) for all existing entries in a project.
session_bootstrapIMPORTANT: On the first user turn of every conversation, including a greeting, call this tool exactly once
session_check_pipeline_statusCheck the status of a Dark Factory pipeline. Returns the current step,
session_cognitive_routeResolve an HDC compositional state into a nearest semantic concept with policy-gated routing.
session_compact_ledgerAuto-compact old session ledger entries by rolling them up into AI-generated summaries.
session_detect_driftDetect whether the current agent session has semantically drifted from its
session_export_memoryExport all of a project's memory to a local file.
session_forget_memoryForget (delete) a specific memory entry by its ID.
session_health_checkwrite actionRun integrity checks on the agent's memory (like fsck for filesystems).
session_intuitive_recallManually trigger the Sparse Distributed Memory (SDM) Intuitive Recall to surface latent patterns
session_load_contextLoad session context for a project using progressive context loading.
session_route_promptCall this at the START of any turn where the user states a NEW task, changes the kind of work, or reports a
session_save_experienceRecord a typed experience event. Unlike session_save_ledger (flat logs),
session_save_handoffUpsert the latest project handoff state for the next session to consume on boot.
session_save_imageSave a local image file into the project's permanent visual memory.
session_save_ledgerSave an immutable session log entry to the session ledger.
session_search_memorySearch session history semantically (by meaning, not just keywords).
session_start_pipelineStart an autonomous Dark Factory pipeline. The pipeline runs in the background
session_synthesize_edgesStep 3A Edge Synthesis: Scans recent project entries with embeddings, finds high-similarity
session_task_routeAnalyze a coding task and recommend whether it should be handled by the host
session_view_imageRetrieve an image from visual memory using its ID.
skill_manageManage scoped skills and platform-skill activation. Actions: list (your skills, team skills, releases);
skill_saveSave a skill at one of three scopes: local (this machine only, works signed out),
sync_pull_handoffPulls this account's synced handoff for a project from the E2E relay and
verify_behaviorCall BEFORE editing behavioral source files (API routes, ordering logic, billing, auth, migrations).
Public scan report
scanner v0.1.5 · 2026-09-19 · same rubric, same numbers if you re-run it
- Code scan191 source files scanned15/25
- –Live reliabilityno gateway calls yet and no remote to proben/a
- –Tool poisoningtools not inspected (local package is not executed); not countedn/a
- Auth qualitystatic API keys via environment variables6/15
- Maintenancelast push 0 days ago15/15
- Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
Findings (2)
- mediumnpm install lifecycle script present
install.script - mediumnpm install lifecycle script present
install.scriptpackage.json: …e dist/utils/universalImporter.js", "postinstall": "node -e \"import('./dist/postinstall.j…
Grade history
- 2026-09-19restoreD → Cscore 68: npm install lifecycle script present; npm install lifecycle script present
Install directly
Runs npx -y prism-mcp-server on your machine. Read the scan report first; the gateway never runs local packages.
claude mcp add prism-coder -- npx -y prism-mcp-server
Prism Coder: common questions
- Is Prism Coder MCP server safe?
- With care: it is graded C, so read the findings first (68/100). Read the Prism Coder safety report
- How do I install Prism Coder?
- It runs on your machine. Copy the Claude Code, Claude Desktop or Cursor config from the install section.
- Does Prism Coder need an API key?
- Yes. The registry entry asks for
BRAVE_API_KEY,GEMINI_API_KEY,SUPABASE_KEY. - Is Prism Coder maintained?
- The last commit was in the last day (2026-09-19). The latest release is v20.21.8.
- What can I use instead of Prism Coder?
- Servers from other publishers that do the same job: Deja Vu MCP server, Memorix MCP server and Plur MCP server. Compare all Prism Coder alternatives.
Alternatives to Prism Coder
Same job from other publishers: the closest match first, then the best rated.
- Deja Vudeja-vu: local memory over the session histories of thirty-three coding agents.not reviewedEstablishedA
MemorixLocal-first project memory with legacy MCP and 2026 discovery compatibility.not reviewedEstablishedB- PlurOpen, local-first engram memory for AI agents: read, correct, delete; shared over MCP.not reviewedEstablishedA
- Nautilus Compass MemoryLocal-first long-term memory for AI agents, with byte-recomputable signed verification receipts.not reviewedEstablishedB
- VestigeLocal-first memory for AI agents that reaches backward to find a failure's root cause.not reviewedEstablishedB