Agishub MCP vs Codebase Memory MCP
A side-by-side look at the Agishub MCP and Codebase Memory MCP MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.
Verdict: choose Agishub MCP for knowledge & memory work as a local process; choose Codebase Memory MCP for knowledge & memory as a local process. You can also run both side by side in one mcpServers block.
Which MCP server should you choose?
Choose Agishub MCP when
- You need dedicated capabilities in the Knowledge & Memory domain.
- You prefer a local stdio subprocess transport.
- You want tools like
ai.chat, ai.classify, ai.embed.
Choose Codebase Memory MCP when
- You need dedicated capabilities in the Knowledge & Memory domain.
- You prefer a local stdio subprocess transport.
- Its auth model fits you: No auth required.
- You want tools like
index_repository, search_graph, query_graph.
Feature & specification comparison
Rows where the two servers differ are marked.
| Spec | ||
|---|---|---|
| Category | Knowledge & Memory | Knowledge & Memory |
| Quality signal | 53/100 · Good | 73/100 · Great |
| Install command | Confirmed | Confirmed |
| Transport | Local subprocess (stdio) | Local subprocess (stdio) |
| Auth | Not declared | No auth required |
| Pricing | Not declared | Free |
| Required env vars | None listed | None listed |
| Verified owner | Community listing | Community listing |
| GitHub stars | 0 | 47,236 |
| Directory activity | 0 views 0 installs 0 upvotes | 8 views 1 installs 1 upvotes |
| Tools | 34 | 17 |
| Full listing | View Agishub MCP | View Codebase Memory MCP |
Tools & capabilities
Agishub MCP tools 34
ai.chatAsk a general-purpose LLM a question or give it an instruction, with an optional system prompt. No external API key required.ai.classifyClassify a text into exactly one of the candidate labels you provide (e.g. sentiment, topic, intent).ai.embedTurn text into a numeric embedding vector for semantic search, RAG and similarity. Multilingual.ai.extractExtract named entities from text — people, organizations, locations, dates and miscellaneous — returned as structured JSON.ai.summarizeSummarize a block of text into a short abstract, with an optional target length. No external API key required.web.browserDrive a headless browser: open a URL and run an ordered list of steps — click, type, press keys, wait, extract text and screenshot. For flows the plain scraper can't reach (logins, forms, multi-step pages).web.crawlCrawl multiple pages of a site, respecting link depth and domain limits. Returns async job_id; results include markdown or HTML per page. Use it to fetch and process many pages of content at once.web.extractFetch any public web page and return its main content as clean, token-efficient Markdown (title, description, headings, links, lists). Set render:true to execute JavaScript first for single-page apps or JS-heavy pages that would otherwise come back empty. Built for RAG and for agents that need to r…web.extract_structuredAI-powered structured extraction: give a URL plus a natural-language prompt and/or a JSON Schema, and get back clean structured JSON (e.g. product name, price, rating). Renders the page in a headless browser first, so it works on SPAs.web.linksReturn every hyperlink on a JavaScript-rendered page as a list of absolute URLs, with options to keep only visible links or only same-site links. Backed by a headless browser. Use it to map a site or seed a crawler.web.mapDiscover all URLs reachable from a domain within a link depth limit. Returns a flat list of absolute URLs, respects robots.txt crawl delays. Use it to map a site's structure before crawling.web.scrapeExtract specific elements from a JavaScript-rendered page by CSS selector. Give a list of selectors (e.g. 'h1', '.price', 'a.product') and get back the text and attributes of every match. Backed by a headless browser, so it works on SPAs and JS-heavy pages.- +22 more on the listing page
Codebase Memory MCP tools 17
index_repositoryIndex a repository. full/moderate add semantics; fast omits them; cross-repo-intelligence links services. Reports coverage gaps.search_graphFind symbols via BM25 query, regex name/qn filters, or semantic_query. Rows keep qn/file/lines and in/out over CALLS/USAGE/CALL_REFERENCE/INHERITS/IMPLEMENTS.query_graphRead-only Cypher for multi-hop, aggregation, complexity, or cross-service analysis. Default: 200 visible rows with exact/lower-bound totals and truncation; continue safely with next_cursor. graph=missed is a file tree of flagged coverage gaps; absence is not proof of completeness. Use get_graph_schema(diagnostics=full) for properties.trace_pathTrace callers/callees, data flow, or cross-service paths. Defaults exclude tests and resolver evidence. Rows keep qn/hop with explicit totals, relations, and continuations.get_code_snippetRead a search_graph symbol. auto bounds source and outlines large containers; full restores up to 500 lines. Source/outline pages continue; coverage_note marks gaps.get_file_outlineDeclaration outline of one exact repository-relative file: optional exact label filter, source order, exact total/offset/limit paging; file/folder/container nodes excluded.get_graph_schemaGet node-label and edge-type counts. diagnostics=full also lists queryable properties.compare_graphsCompare two indexed snapshots: deterministic target-only additions and base-only removals of stable node/edge identities; each set capped by limit and a 512 KiB budget with exact totals and truncation reasons.get_architectureCompact counts, languages, packages, entry points. Request structure, dependencies, routes, hotspots, boundaries, layers, clusters, cycles, or file_tree; path scopes a directory.search_codeGraph-ranked text search: compact symbols, full bounded source, or file paths.list_projectsList projects with stable paging. Identity is lean; stats adds graph sizes.delete_projectDelete a project from the index- +5 more on the listing page
Ready-to-paste client configs
Paste either block (or both) into your client config, e.g. claude_desktop_config.json or ~/.cursor/mcp.json. We only show a config when the install command is confirmed.
Agishub MCP
{
"mcpServers": {
"agent-memory": {
"command": "npx",
"args": [
"-y",
"@agishub/mcp"
]
}
}
}
Codebase Memory MCP
{
"mcpServers": {
"deusdata-codebase-memory-mcp": {
"command": "npx",
"args": [
"-y",
"codebase-memory-mcp"
]
}
}
}
Frequently asked questions
Agishub MCP is categorized under Knowledge & Memory and uses a local stdio subprocess. Codebase Memory MCP belongs to Knowledge & Memory and uses a local stdio subprocess. Pick Agishub MCP for knowledge & memory work and Codebase Memory MCP for knowledge & memory.
Copy the mcpServers block from the config section on this page into your client's config (for example claude_desktop_config.json or ~/.cursor/mcp.json), then fully restart the client.
Agishub MCP has no declared pricing — check the project's own site. Codebase Memory MCP is listed as free. Auth: no auth required. If a server needs environment variables such as API keys, define them under the env key in your client's MCP config.
Yes. MCP clients support multiple servers: add agent-memory and deusdata-codebase-memory-mcp as separate keys in the same mcpServers object, and your assistant will call tools from either one.
On AllMCPs, Agishub MCP has a quality signal of 53/100 (Good) with 0 views, 0 installs and 0 GitHub stars. Codebase Memory MCP has 73/100 (Great) with 8 views, 1 installs and 47,236 GitHub stars.