diff --git a/README.md b/README.md
index 78b929598..ddad786ac 100644
--- a/README.md
+++ b/README.md
@@ -1206,6 +1206,7 @@ Tools and integrations that enhance the development workflow and environment man
 - [paladini/devutils-mcp-server](https://github.com/paladini/devutils-mcp-server) [![paladini/devutils-mcp-server MCP server](https://glama.ai/mcp/servers/paladini/devutils-mcp-server/badges/score.svg)](https://glama.ai/mcp/servers/paladini/devutils-mcp-server) 📇 🏠 🍎 🪟 🐧 - 36 zero-auth developer utilities: MD5/SHA/bcrypt hashing, Base64/hex/URL encoding, UUID/password/passphrase generation, JWT decoding, JSON/YAML/XML formatting, timestamp conversion, CIDR calculator, and text tools.
 - [paracetamol951/P-Link-MCP](https://github.com/paracetamol951/P-Link-MCP) 🏠 🐧 🍎 ☁️ - Implementation of HTTP 402 (payment required http code) relying on Solana
 - [mcpware/pagecast](https://github.com/mcpware/pagecast) [![mcpware/pagecast MCP server](https://glama.ai/mcp/servers/mcpware/pagecast/badges/score.svg)](https://glama.ai/mcp/servers/mcpware/pagecast) 📇 🏠 - Record any browser page as GIF or video. AI-driven demo recording with scroll/click/hover interactions via Playwright + ffmpeg. `npx @mcpware/pagecast`
+- [Perseus-Computing-LLC/perseus](https://github.com/Perseus-Computing-LLC/perseus) [![Perseus-Computing-LLC/perseus MCP server](https://glama.ai/mcp/servers/Perseus-Computing-LLC/perseus/badges/score.svg)](https://glama.ai/mcp/servers/Perseus-Computing-LLC/perseus) 🐍 🏠 🍎 🪟 🐧 - Local-first live context engine and MCP server. Pre-resolves git, services, tests, and memory into a ready context briefing at session start (compile-before-context). MIT, PyPI: perseus-ctx.
 - [Pharaoh-so/pharaoh](https://github.com/0xUXDesign/pharaoh-mcp) [![pharaoh MCP server](https://glama.ai/mcp/servers/@Pharaoh-so/pharaoh/badges/score.svg)](https://glama.ai/mcp/servers/@Pharaoh-so/pharaoh) 📇 ☁️ 🍎 🪟 🐧 - Hosted MCP server that parses TypeScript and Python codebases into Neo4j knowledge graphs for blast radius analysis, dead code detection, dependency tracing, and architectural context.
 - [picahq/mcp](https://github.com/picahq/mcp) 🎖️ 🦀 📇 ☁️ - One MCP for all your integrations — powered by [Pica](https://www.picaos.com), the infrastructure for intelligent, collaborative agents.
 - [jcooley8/pincushion-plugin](https://github.com/jcooley8/pincushion-plugin) [![jcooley8/pincushion-plugin MCP server](https://glama.ai/mcp/servers/jcooley8/pincushion-plugin/badges/score.svg)](https://glama.ai/mcp/servers/jcooley8/pincushion-plugin) 📇 ☁️ 🏠 🍎 🪟 🐧 - Visual feedback as agent work packets. Stakeholders drop pins on your live app; your AI coding agent reads each pin (selector, screenshot, DOM snippet, thread, acceptance criteria) via MCP and ships the fix, recording the commit/branch/PR on resolve. Install: `npx pincushion-mcp`.
@@ -1334,7 +1335,6 @@ Tools and integrations that enhance the development workflow and environment man
 - [NazarKalytiuk/tarn](https://github.com/NazarKalytiuk/tarn) [![NazarKalytiuk/tarn MCP server](https://glama.ai/mcp/servers/NazarKalytiuk/tarn/badges/score.svg)](https://glama.ai/mcp/servers/NazarKalytiuk/tarn) 🦀 🏠 🍎 🪟 🐧 - CLI-first API testing tool with structured JSON failures (`failure_category`, `error_code`, `hints`) so AI agents can branch on the taxonomy without parsing stderr. MCP tools: `tarn_run`, `tarn_validate`, `tarn_fix_plan`, `tarn_inspect`, `tarn_rerun_failed`, and more. Tests are `.tarn.yaml`. Single static binary (musl), MIT.
 - [tooluse-labs/perfetto-mcp-rs](https://github.com/tooluse-labs/perfetto-mcp-rs) [![tooluse-labs/perfetto-mcp-rs MCP server](https://glama.ai/mcp/servers/tooluse-labs/perfetto-mcp-rs/badges/score.svg)](https://glama.ai/mcp/servers/tooluse-labs/perfetto-mcp-rs) 🦀 🏠 🍎 🪟 🐧 - MCP server for [Perfetto](https://perfetto.dev) trace analysis. Runs PerfettoSQL queries on `.perfetto-trace` / `.pftrace` files via auto-downloaded `trace_processor_shell`, with dedicated Chrome tools for page loads, scroll jank, main-thread hotspots, and stdlib module discovery. Cross-client tested on Claude Code and Codex. Available via `cargo install`, Homebrew tap, and curl install script.
 - [mshegolev/jaeger-mcp](https://github.com/mshegolev/jaeger-mcp) [![mshegolev/jaeger-mcp MCP server](https://glama.ai/mcp/servers/mshegolev/jaeger-mcp/badges/score.svg)](https://glama.ai/mcp/servers/mshegolev/jaeger-mcp) 🐍 ☁️ 🏠 – Jaeger distributed tracing MCP. 5 tools: list_services, list_operations, search_traces, get_trace, get_dependencies. Any Jaeger instance (HTTP API v3); PyPI + MCP Registry.
-- [tcconnally/perseus](https://github.com/tcconnally/perseus) [![tcconnally/perseus MCP server](https://glama.ai/mcp/servers/tcconnally/perseus/badges/score.svg)](https://glama.ai/mcp/servers/tcconnally/perseus) 🐍 - Compile-before-context MCP server with 13 tools. Pre-resolves workspace state (git, services, file ops, memory federation, multi-agent coordination) into markdown briefings. Single-file Python, MIT. Published as io.github.tcconnally/perseus.
 
 - [parasxos/cpp26-adapter](https://github.com/parasxos/cpp26-adapter) [![parasxos/cpp26-adapter MCP server](https://glama.ai/mcp/servers/parasxos/cpp26-adapter/badges/score.svg)](https://glama.ai/mcp/servers/parasxos/cpp26-adapter) 🐍 🏠 🍎 🪟 🐧 - C++26 paper reference MCP (`cpp26-ref`) backing a Claude Code plugin: `lookup_paper`, fuzzy `search`, `compiler_status` over a 216-paper ISO/IEC 14882:2026 corpus. The plugin's skill + reviewer subagent use these tools to bias Claude toward reflection, contracts, `std::execution` senders, `#embed`, expansion statements — even when the local compiler lags. 95% on a held 39-task eval gate.
 - [graphpilot-oss/graphpilot](https://github.com/graphpilot-oss/graphpilot) [![graphpilot-oss/graphpilot MCP server](https://glama.ai/mcp/servers/graphpilot-oss/graphpilot/badges/score.svg)](https://glama.ai/mcp/servers/graphpilot-oss/graphpilot) 📇 🏠 🍎 🪟 🐧 - Structural memory for coding agents. Indexes TypeScript/JavaScript repos and exposes callers, callees, blast-radius impact, and symbol locations over MCP — with file:line@sha evidence anchors and branch-aware differential impact — so agents answer "who calls X?" / "what breaks if I change X?" without re-reading files. Local-only, zero telemetry, Apache-2.0. `npx @graphpilot-oss/graphpilot mcp`