fish-bridge — Session Knowledge Graph MCP server
io.github.MakeaMouse/fish-bridge-mcp·v0.1.3·2 starsCompresses AI chat sessions into a typed knowledge graph. Local/offline via Ollama.
2 stars17 downloads/wk
Reviews
Write oneNobody has reviewed fish-bridge — Session Knowledge Graph yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
fish-bridge — Session Knowledge Graph tools (9)
write = sends, deletes, buys or postsRead from the package source without running it. The installed server may list more.
add_nodeManually add a node to the session graph.
export_sessionReturn the full session graph as a JSON string.
get_contextReturn the current compressed session context as XML.
get_focusReturn a query-scoped subgraph context XML.
import_sessionLoad a prior session graph and merge it into the current session.
list_deferredReturn all deferred items in the current session as plain text.
mark_resolvedMark a question, task, or error as resolved.
record_turnIngest one user/assistant exchange into the session graph.
show_activeReturn the active session thread as plain text (not XML).
Public scan report
scanner v0.1.9 · 2026-09-27 · same rubric, same numbers if you re-run it
- Code scan43 source files scanned25/25
- –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 59 days ago12/15
- Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
How fish-bridge — Session Knowledge Graph compares
Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.
- Safety score
- 78/100
- higher than 57% of 48,255 servers
- Tools
- 9
- the typical server has 7
- Tools that change things
- 0%
- typical: 0%. Fewer write tools means less an agent can break
- GitHub stars
- 2
- more than 75% of 28,688 servers
- Downloads a week
- 17
- more than 5% of 12,191 servers with a package
What its tools let an agent do: 6 read · 2 create · 1 change
Install fish-bridge — Session Knowledge Graph in Claude Code, Cursor or VS Code
claude mcp add fish-bridge-mcp -- uvx fish-bridge-mcp
What the publisher says
From the fish-bridge — Session Knowledge Graph repository's README, as published. We do not edit it. Read it on GitHub
fish_bridge
<!-- mcp-name: io.github.MakeaMouse/fish-bridge-mcp -->
Session-scoped knowledge graph engine for AI chat context compression.
Converts raw AI chat (40k+ tokens) into a compact typed knowledge graph (~300–800 tokens) and writes it to .github/copilot-instructions.md or CLAUDE.md — automatically included in every AI turn across all modes (ask, edit, agent). No MCP server required for the core workflow.
Raw session (40k tokens) → [fish_bridge] → Compressed graph (350 tokens)
written to copilot-instructions.md
picked up by every AI turn automaticallyInstall
Don't have uv? Get it first: curl -LsSf https://astral.sh/uv/install.sh | sh (macOS/Linux) or see uv docs. It replaces pip + pipx + pyenv in one tool — no virtualenv management needed.
Recommended — uv tool install (installs both the fish-bridge CLI and fish-bridge-mcp MCP server on your PATH):
# Local Ollama backend — free, offline (requires Ollama running)
uv tool install fish-bridge-mcp
# Gemini backend (~$0.0002/turn, ~95% quality — recommended cloud option)
uv tool install "fish-bridge-mcp[gemini]"
export GEMINI_API_KEY=...
# Claude backend (~$0.002/turn, ~97% quality)
uv tool install "fish-bridge-mcp[claude]"
export ANTHROPIC_API_KEY=sk-ant-...
# OpenAI backend (~$0.0003/turn, ~93% quality)
uv tool install "fish-bridge-mcp[openai]"
export OPENAI_API_KEY=sk-...
# Everything
uv tool install "fish-bridge-mcp[all]"After install, two commands are available on your PATH:
- fish-bridge — the main CLI (ingest, compile, show, serve, ...)
- fish-bridge-mcp — the MCP server for VS Code agent mode
MCP config only (no permanent install needed): use uvx directly in your .vscode/mcp.json — it downloads and runs the MCP server on demand:
{ "command": "uvx", "args": ["fish-bridge-mcp"] }See the MCP server section below for the full config.
Traditional pip install (for embedding fish-bridge as a library in your own Python project)
pip install fish-bridge-mcp
pip install "fish-bridge-mcp[gemini]" # with Gemini backend
pip install "fish-bridge-mcp[claude]" # with Claude backend
pip install "fish-bridge-mcp[all]" # everything2-minute quickstart
# 1. Initialize for your project
fish-bridge init --tool copilot --project ./
# 2. Ingest the latest Copilot session (auto-discovers JSONL on macOS/Linux/Windows)
fish-bridge ingest --source copilot
# 3. View the graph
fish-bridge show
# 4. Compile to your instructions file (done automatically after ingest)
fish-bridge compileThat's it. .github/copilot-instructions.md now contains a ~350-token compressed summary of your session, replacing raw history in every future turn.
Backends
Configure with:
fish-bridge config --backend geminiShortened. The full README is on GitHub.
Nothing above is checked by us. What we check is on the safety report.
fish-bridge — Session Knowledge Graph: common questions
- Is fish-bridge — Session Knowledge Graph MCP server safe?
- Mostly: it is graded B (78/100). Read the fish-bridge — Session Knowledge Graph safety report
- How do I install fish-bridge — Session Knowledge Graph?
- It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
- Does fish-bridge — Session Knowledge Graph need an API key?
- Yes. The registry entry asks for
ANTHROPIC_API_KEY,OPENAI_API_KEY,GEMINI_API_KEY. - Is fish-bridge — Session Knowledge Graph maintained?
- The last commit was 97 days ago (2026-07-30). The latest release is v0.1.3.
- What can I use instead of fish-bridge — Session Knowledge Graph?
- Servers from other publishers that do the same job: Codebase Memory MCP server and Neo4j Memory MCP server.
- How does fish-bridge — Session Knowledge Graph compare with other MCP servers?
- safety score 78/100 (higher than 57% of 48,255 servers); tools 9 (the typical server has 7); tools that change things 0% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.
Alternatives to fish-bridge — Session Knowledge Graph
Same job from other publishers: the closest match first, then the best rated.
- Codebase MemoryCodebase knowledge graph for AI agents — 162 languages, sub-ms queries, 99% fewer tokens.not reviewedWidely usedC
- Neo4j MemoryMCP Neo4j Knowledge Graph Memory Servernot reviewedEstablishedA