Agentward vs Masnavi
A side-by-side look at the Agentward and Masnavi MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.
AgentwardSecurity · Local subprocess (stdio)Permission control plane for AI agents. MCP proxy that enforces least-privilege YAML policies on every tool call, classifies sensitive data (PII/PHI), detects dangerous skill chains, and generates compliance audit trails. Supports stdio and HTTP proxy modes.47FairAuth: no auth requiredVerdict: choose Agentward for security work as a local process; choose Masnavi for security over a hosted endpoint. You can also run both side by side in one mcpServers block.
Which MCP server should you choose?
Choose Agentward when
- You need dedicated capabilities in the Security domain.
- You prefer a local stdio subprocess transport.
- Its auth model fits you: No auth required.
Choose Masnavi when
- You need dedicated capabilities in the Security domain.
- You prefer a remote HTTP/SSE transport.
- You want tools like
search, search_meaning, lookup.
Feature & specification comparison
Rows where the two servers differ are marked.
| Spec | Agentward | |
|---|---|---|
| Category | Security | Security |
| Quality signal | 47/100 · Fair | 53/100 · Good |
| Install command | Confirmed | Confirmed |
| Transport | Local subprocess (stdio) | Remote HTTP/SSE |
| Auth | No auth required | Not declared |
| Pricing | Free | Not declared |
| Required env vars | None listed | None listed |
| Verified owner | Community listing | Community listing |
| GitHub stars | 19 | 0 |
| Directory activity | 7 views 0 installs 0 upvotes | 1 views 0 installs 0 upvotes |
| Tools | Not listed | 13 |
| Full listing | View Agentward | View Masnavi |
Tools & capabilities
Agentward tools
No tool names declared yet. Check the project README from the listing page.
Masnavi tools 13
searchFull-text search across the Masnavi. Returns beyts that contain the query terms, ranked by relevance. Useful for finding where a theme, word, or phrase appears.search_meaningSemantic search: find the beyts closest in MEANING to the query, in ANY language — English, Persian, Spanish, Turkish, Arabic, … . Use this when you have a theme, feeling, or idea rather than exact Persian words (e.g. 'feeling separated from your origin' → M1:1). Each hit carries a cosine-similarity score. status='unavailable' means the vector index is not built yet — fall back to `search`.lookupFetch a specific beyt by its citation (e.g. 'M3:1278'), by daftar+beyt number, or by global beyt index. Optionally include surrounding beyts for context.verifyGiven a candidate quote attributed to Rumi's Masnavi, check whether it actually appears. Returns status='exact' (with citation), 'fuzzy' (with similar candidates), or 'not_found'. USE THIS BEFORE QUOTING RUMI to avoid hallucination.get_sectionRetrieve a full section (story / بخش) with all its beyts.table_of_contentsBrowse the Masnavi's section list. Returns titled sections per daftar with beyt counts and ranges.random_beytReturn a randomly-selected beyt, optionally restricted to a daftar.get_rangeFetch ALL beyts between two endpoints, inclusive, grouped by section. Use this — NOT many calls to get_section or lookup — when a user asks for a full story, a long passage, or a sequence of beyts spanning multiple sections. Endpoints are canonical citations like 'M2:2608' and 'M2:2775', or global indices via start_global / end_global. Max range: 500 beyts.find_sectionsFind sections (stories) by TITLE. Exact words first (phrase, then AND-of-tokens); when NO title contains the words, falls back to MEANING matches in any language (hits carry match='meaning' + a cosine score — verify with get_section before relying on one). Each match includes `first_citation` and `last_citation` — ready-to-use canonical citations (e.g. 'M2:2608'). To read a whole multi-section story, call get_range with the FIRST match's `first_citation` as start and the LAST match's `last_citation` as end. Do NOT construct a citation from `first_beyt_global` — that is a GLOBAL index (1..25635), not a daftar-local beyt number. Example: find_sections('ابلیس معاویه', daftar=2).explainGet commentary (Persian + English) for a specific beyt of the Masnavi, attributed to a primary source (e.g. Abdolkarim Soroush's lectures). Returns the beyt text along with structured commentary entries. Each entry has source, author, language, body markdown, and confidence ('ai-draft' / 'reviewed' / 'verbatim'). Use this when a user asks 'what does this beyt mean' or 'what does <scholar> say about M1:1'.search_divanFull-text search across the 34,603 beyts of the ghazals of the Divan-e Shams (Divan-e Kabir) — Rumi's lyric work, distinct from the Masnavi. Returns beyts with divan citations (G{ghazal}:{beyt}, e.g. G1393:1). Use when you know the exact Persian words; use search_divan_meaning for a theme in any language.search_divan_meaningSemantic search over the Divan-e Shams ghazals: given a theme, feeling, or idea in ANY language, returns the GHAZALS closest in meaning — each with its best-matching couplet as a preview and a cosine score. Both couplet-level and whole-ghazal vectors are searched, so a ghazal whose overall theme matches is found even when no single couplet does. Fetch a full ghazal with get_ghazal. status='unavailable' means the index is not built — fall back to search_divan.- +1 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.
Agentward
{
"mcpServers": {
"agentward-ai-agentward": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-filesystem"
]
}
}
}
Masnavi
{
"mcpServers": {
"masnavi": {
"url": "https://masnavi.ai/mcp"
}
}
}
Frequently asked questions
Agentward is categorized under Security and uses a local stdio subprocess. Masnavi belongs to Security and uses a remote HTTP/SSE transport. Pick Agentward for security work and Masnavi for security.
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.
Agentward is listed as free. Auth: no auth required. Masnavi has no declared pricing — check the project's own site. 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 agentward-ai-agentward and masnavi as separate keys in the same mcpServers object, and your assistant will call tools from either one.
On AllMCPs, Agentward has a quality signal of 47/100 (Fair) with 7 views, 0 installs and 19 GitHub stars. Masnavi has 53/100 (Good) with 1 views, 0 installs and 0 GitHub stars.