# io.github.dcostenco/prism-coder (io.github.dcostenco/prism-coder@20.21.2) > Source: > Published: 2026-09-17 00:00:37+00:00 [← Index](https://mcpindex.ai/leaderboard) # io.github.dcostenco/prism-coder Session memory for coding agents: local-first recall, drift detection, on-device inference. The current version, v20.21.2, was published to the official MCP registry on 2026-09-17. It is distributed as prism-mcp-server on npm, filed under Memory & RAG by this index, and declares 8 environment variables. Removals and unreachable sources are measured across every server this index tracks, contract drift across the servers that answer in consecutive snapshots; [the index's current counts](https://mcpindex.ai/stats) put this record in context. ## Using io.github.dcostenco/prism-coder in Claude, Cursor, Gemini CLI, Cline, or Zed? MCP tool contracts can change remotely with no version bump. The mcpindex gate pins each contract and **HOLDs the call** when it drifts-before your agent acts. Zero credentials. This is not the package install for this server itself (use **Install this server** for that). Rewrites your MCP host config so each server launches behind the gate. Inspect first: curl -fsSL https://mcpindex.ai/install.sh | less ``` uv tool install mcpindex-gate && mcpindex-config-wire ``` [method](https://mcpindex.ai/methodology) Semantic screen found no manipulation pattern in the description. Conformance probe not yet run. `mcpindex.integrity.description` passINFO evidence“No suspicious instructions or data handling mentioned”via static_description - - Semantic screen only - the deterministic conformance probe has not run on this server - - Confidence is reported but not yet calibrated (v1) - - Screen reads the tool description, not the live behavior - - advisory - - registry description only no input schema - - screen model 8b - - Still current: the description we screened is unchanged, re-checked against the registry - - The registry listing (version, packages, links) changed after this screen ran - the description we assessed did not Semantic screen: an LLM judge reads the tool description for hidden instructions (status PARTIAL). A pass means the description is not lying, not that the tool is safe: a high-capability tool with an honest description still warrants caution. The deterministic conformance probe has not been run on this server yet, so the screen here is semantic-only. Posture: advisory. Confidences are reported but not yet calibrated (calibrated=false at v1). Full verdict history is not shown on this page. Own this server? [Screen its description →](https://mcpindex.ai/screen) ## That verdict was true at screening time (snapshot 2026-09-17). Contracts can change after screening, with no version bump. The gate pins io.github.dcostenco/prism-coder’s tool contracts on first sight and holds any silent change before your agent acts - the check that keeps being true on Tuesday. [See your first HOLD in 2 minutes →](https://mcpindex.ai/guides/install-the-gate-first-hold) Related: [how to trust an MCP server](https://mcpindex.ai/guides/how-to-trust-an-mcp-server) · [screen before install](https://mcpindex.ai/guides/screen-mcp-server-before-install) · [silent contract drift](https://mcpindex.ai/guides/mcp-silent-contract-drift) People vet a server before wiring it in. One line on your project site or docs answers that with an independent record: screening verdict, registry provenance, contract drift history. It stays current as new screens and drift events land. ``` [Independent trust record for io.github.dcostenco/prism-coder](https://mcpindex.ai/server/io-github-dcostenco-prism-coder) - screening verdict, registry provenance, and contract drift monitoring. Independent trust record for io.github.dcostenco/prism-coder - screening verdict, registry provenance, and contract drift monitoring. ``` A live verdict badge for your README or listing. It reflects the current screen, links back here, and updates when the verdict does. ``` [![mcpindex](https://mcpindex.ai/api/v1/badge/io-github-dcostenco-prism-coder)](https://mcpindex.ai/server/io-github-dcostenco-prism-coder) mcpindex verdict ``` `BRAVE_API_KEY` Brave Search API key for web search tools `GEMINI_API_KEY` Google Gemini API key for AI-powered summarization and embeddings `SUPABASE_URL` Supabase project URL for session memory and knowledge persistence `SUPABASE_KEY` Supabase service role key for database access `PRISM_USER_ID` User ID for multi-tenant row-level security isolation (defaults to 'default') `GCP_PROJECT_ID` Google Cloud project ID for Vertex AI Discovery Engine integration `VERTEX_LOCATION` Vertex AI location/region (defaults to 'global') `VERTEX_DATA_STORE_ID` Vertex AI Discovery Engine data store ID for enterprise search [methodology](https://mcpindex.ai/methodology) [Fodda Knowledge Graphsai.fodda/mcp-server](https://mcpindex.ai/server/ai-fodda-mcp-server) Expert-curated knowledge, brand, research & earnings intelligence — 47 tools, 220+ graphs. [Ambercom.ambermem/amber](https://mcpindex.ai/server/com-ambermem-amber) Long-term memory for AI assistants. Hybrid retrieval, query expansion, auto-topics. [DeepMemio.github.deepmemteam/deepmem](https://mcpindex.ai/server/io-github-deepmemteam-deepmem) Mem0-compatible persistent memory for AI agents: write facts once, recall them semantically.