Agent Recall vs Leghis Smart Thinking
A side-by-side look at the Agent Recall and Leghis Smart Thinking MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.
Verdict: choose Agent Recall for knowledge & memory work as a local process; choose Leghis Smart Thinking 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 Agent Recall 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
session_start, session_end, remember.
Choose Leghis Smart Thinking when
- You need dedicated capabilities in the Knowledge & Memory domain.
- You prefer a local stdio subprocess transport.
- You want tools like
capabilities, run_create, run_get.
Feature & specification comparison
Rows where the two servers differ are marked.
| Spec | ||
|---|---|---|
| Category | Knowledge & Memory | Knowledge & Memory |
| Quality signal | 71/100 · Great | 65/100 · Great |
| Install command | Confirmed | Confirmed |
| Transport | Local subprocess (stdio) | Local subprocess (stdio) |
| 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 | 372 | 33 |
| Directory activity | 6 views 0 installs 0 upvotes | 2 views 0 installs 0 upvotes |
| Tools | 5 | 43 |
| Full listing | View Agent Recall | View Leghis Smart Thinking |
Tools & capabilities
Agent Recall tools 5
session_start[ENTRY — call FIRST, before acting] Use when the user asks to start, load, continue, resume, or open memory for a project. Set mode='lite' for a ≤500-token briefing (good for fresh conversations where the agent will pull memory on demand via recall()).session_end[ON SAVE/EXIT — YOU must call this; nothing auto-saves] Use when the user asks to save, checkpoint, summarize, end, retain, or persist the current session. Optionally pass close_phase / open_phase to update the project pipeline narrative spine in the same call.remember[MID-SESSION WRITE — single fact/decision; saying it is not saving it] Use when the user asks to remember, store, note, or save a specific decision, fact, or insight.recall[RETRIEVE — use freely, any time] Use when the user asks to recall, search, find, or look up previous memory, context, or decisions.check[MID-SESSION — safe any time; for alignment, before risky decisions] Use when the user asks to validate understanding, verify alignment, or check if their interpretation matches the human's intent. Also call BEFORE a high-risk action — publish, deploy, delete, credential exposure, external send/message, or any other irreversible write — passing `action_description` (one sentence, what you're about to do). Returns matching corrections/rules/insights plus a `verdict`: `blocked` means an authoritative correction OVERRIDES the plan — read it before proceeding. To RECORD a durable human correction, pass `human_correction` as the STRUCTURED object {rule, why, applies_when} — a plain string is only STAGED for later review, never activated.
Leghis Smart Thinking tools 43
capabilitiesDescribe configured capabilities and explicit limits, including dossier capacity, scientific worker bounds, build metadata, the software supervisor (rubrics, review policy, approved recipes and execution) and the published catalogue fingerprint.run_createCreate an owned dossier when you need tracked claims, evidence with sources, coverage or audit. For a single exact check prefer calculate/solve_math/solve_logic instead. Restricted runs stay within server storage. profile picks an operator-approved budget envelope (standard by default; larger envelopes are bounded by the operator policy). For anonymous access the reply embeds a one-time dossier capability in the returned identifier: keep it exactly as returned — it authorizes every later operation on this dossier and is never re-issued.run_getRead a compact owned dossier. Explicit detail=full returns the complete document with its published bounds (mutation receipts omitted; use run_export when a bound is reached), never keys or server policies. presentation=detailed returns unprojected output; the opaque `cursor` continues claim pagination.run_listList owned run summaries with pagination.calculateExact arithmetic without floating-point truth claims. Grammar: rationals, factorial(n), binomial(n,k), gcd, lcm, mod(a,m), powmod(a,e,m), n!, `a mod b`, and ONE top-level comparison (=, !=, <, <=, >, >=). Pure operation: no dossier, no audit record. Supply expected to compare and get matchesExpected.calculate_batchEvaluate independent exact expressions in one call (same kernel and domains as calculate). Partial mode keeps valid items when others fail; atomic mode refuses the whole batch. References between items are not accepted in this version.checkOne-shot structured check without a dossier. Accepts a deterministic ClaimSpec (arithmetic, linear, ordering, boolean) and returns the shared verifier status. Kinds needing artifacts or the symbolic worker are refused with a hint. Exact inputs never call Jev.finite_computeBounded declarative computation: range_reduce (sum/product/count over an inclusive integer range; optional modulus), linear_recurrence (a_n = c0*a_(n-1) + c1*a_(n-2) + ..., coefficients listed most recent first; optional modulus), bounded_search (exhaustive enumeration of a bounded integer space against one comparison predicate). Declarative only: no clock, network, files or dynamic code; a reached limit returns a partial result, never a fake maximum or absence.casIsolated symbolic recipes: identity (expression equal to rhs?), simplify, solve (ONE symbol, univariate polynomial, rational coefficients, degree <= 8, exact roots including multiplicities). Runs only in the separate IAM-protected worker with pinned image; no arbitrary Python and no local fallback. A library result is not proof-kernel certification. assumptions is optional, e.g. "t=real, u=positive". Domain assumptions are applied: roots excluded by the declared domain are reported in excludedRoots and never counted as solutions. The worker bounds are published in capabilities.scientific (expression <= 2000 bytes, <= 8 symbols).solve_mathExact rational linear system solver. Unique, inconsistent and underdetermined are distinct. Pure operation: no dossier required.solve_logicSolve explicitly supplied ordering constraints, without guessing a prose translation. Pure operation: no dossier required.claimRegister an explicit structured claim inside a dossier. The host formalizes text; Jev cannot invent proof inputs.- +31 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.
Agent Recall
{
"mcpServers": {
"agent-recall": {
"command": "npx",
"args": [
"-y",
"agent-recall-mcp"
]
}
}
}
Leghis Smart Thinking
{
"mcpServers": {
"leghis-smart-thinking": {
"command": "npx",
"args": [
"-y",
"smart-thinking-mcp@16.3.1"
]
}
}
}
Frequently asked questions
Agent Recall is categorized under Knowledge & Memory and uses a local stdio subprocess. Leghis Smart Thinking belongs to Knowledge & Memory and uses a local stdio subprocess. Pick Agent Recall for knowledge & memory work and Leghis Smart Thinking 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.
Agent Recall is listed as free. Auth: no auth required. Leghis Smart Thinking 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 agent-recall and leghis-smart-thinking as separate keys in the same mcpServers object, and your assistant will call tools from either one.
On AllMCPs, Agent Recall has a quality signal of 71/100 (Great) with 6 views, 0 installs and 372 GitHub stars. Leghis Smart Thinking has 65/100 (Great) with 2 views, 0 installs and 33 GitHub stars.