Server Details
Precision math engine for AI agents. 203 exact methods. Zero hallucination.
- Status
- Unhealthy
- Last Tested
- Transport
- Streamable HTTP
- URL
- Repository
- Arithym-io/arithym
- GitHub Stars
- 0
- Server Listing
- Arithym
See and control every tool call
Available Tools
1 toolArithymInspect
Exact precision math engine — 209 methods across 22 domains, all arithmetic as exact fractions with zero floating-point error. Use the 'tool' parameter to select a subsystem:
compute — Exact arithmetic, factorization, sqrt, trig, unit conversion. Examples: tool="compute" action="factorize" n="360" | action="sqrt" n="7920"
calculate — Multi-step chains with $prev/$label references. Example: tool="calculate" operations=[{values:["a","b"], read:"multiply", label:"result"}]
reference — Knowledge gateway backed by Epithreads (289 curated entries, 989 searchable aliases, 407 exact values). 118 chemistry (elements + compounds), 82 unit definitions & conversions, 79 physics constants, 10 math constants. Sources: CODATA 2022, IUPAC 2021, SI definitions. Browse: action='query_entries' domain='unit.conversion' | 'chemistry.elements' | 'physics.constants' | 'math.constants'. Lookup by name/symbol: action='lookup' query='Fe' or query='speed of light'. Also: 209 computation methods via action='guide', discover by keyword via action='discover'. call 209 computation methods (matrix, statistics, chemistry, physics, geometry...), discover by keyword. Examples: tool="reference" action="lookup" query="Fe" | action="guide" module="matrix" method="eigenvalues" args="[[4,1],[2,3]]"
model — Computational graph engine (up to 2,000 nodes). Define models, forward-pass, what-if scenarios, solve for target outputs. Graph ops: add, subtract, multiply, divide, power, gcd, lcm, product, sin, cos, tan, log, exp, abs. For large models (50+ nodes), build incrementally with workspace add/derive across multiple calls. Example: tool="model" action="define" spec={...}
workspace — Persistent named values with dependency tracking and cascade updates. State accumulates across calls — build large models incrementally (up to 2,000 nodes). The resulting graph supports the full model toolchain. Example: tool="workspace" action="add" name="mass" value="120"
analyze — Structural comparison (GCD, LCM, prime similarity), cross-domain verification, prime-space projection. Example: tool="analyze" action="compare" a="360" b="540"
optimize — Exact calculus via reverse-mode autodiff. Derivatives, gradients, Jacobians, integrals, critical points, curve analysis. Requires a model. Example: tool="optimize" action="gradient" output_name="total_cost"
| Name | Required | Description | Default |
|---|---|---|---|
| a | No | First operand (compute binary ops, analyze compare) | |
| b | No | Second operand (compute binary ops, analyze compare) | |
| n | No | Number (compute factorize/sqrt, analyze verify) | |
| x | No | ||
| y | No | ||
| z | No | ||
| op | No | Fraction sub-operation: add/subtract/multiply/divide | |
| args | No | JSON arguments for guide method | |
| data | No | JSON workspace data (import) | |
| meta | No | Human-readable description (add, update) | |
| name | No | Value name (workspace add/update/read/link, reference read_domain) | |
| note | No | Note text | |
| spec | No | Model spec: {name, inputs:{name:{value,const?}}, graph:[{name,op,from}], outputs:[names]} | |
| step | No | ||
| tags | No | Comma-separated tags (add) | |
| tier | No | Access tier: core/verified/community | |
| tool | Yes | Subsystem: compute (arithmetic/trig/units), calculate (multi-step chains), reference (constants/guides/discovery), model (graph engine), workspace (persistent values), analyze (compare/verify), optimize (calculus). | |
| unit | No | Angle unit: degrees or radians | |
| const | No | Mark as constant: true/false | |
| delta | No | Perturbation size (sensitivity: 1/1000, hessian: 1/100000) | |
| limit | No | Max results (list_entries, query_entries) | |
| lower | No | Lower integration bound | |
| name1 | No | First value (workspace read comparison) | |
| name2 | No | Second value (workspace read comparison) | |
| names | No | JSON array of workspace names (derive) | |
| order | No | Taylor expansion order (default: 5) | |
| query | No | Search term (lookup: name/symbol, discover: keyword, query_entries: substring) | |
| steps | No | Search steps for critical_points (default: 200) | |
| top_n | No | Max query results (default: 10) | |
| units | No | JSON array of unit strings (unit_check) | |
| upper | No | Upper integration bound | |
| value | No | Value as string — integers, fractions (3/4), decimals (9.81) | |
| action | No | Operation within the selected tool. compute: add/subtract/multiply/divide/power/gcd/lcm/factorize/sqrt/trig/fraction/slide/unit_convert/unit_factor/unit_check/domain_check/list_units. reference: help/discover/guide/lookup/list_methods/list_domains/read_domain/recommend/list_entries/query_entries/db_stats/landmarks. model: define/extend/forward/observe/what_if/solve/learn/sensitivity. workspace: create/add/read/derive/update/link/gcd/lcm/lattice/ratios/query/cluster/snapshot/export/import/diff/note/notes/clear_notes. analyze: compare/verify/project/route/sensitivity. optimize: derivative/gradient/jacobian/hessian/taylor/integral/critical_points/tangent/curve_analysis/optimize/learn. | |
| domain | No | Domain prefix filter (list_entries, query_entries, landmarks) | |
| inputs | No | JSON array of inputs (domain_check) | |
| method | No | Method within module (guide — e.g. 'determinant', 'molar_mass') | |
| module | No | Domain module (guide, list_methods — e.g. 'matrix', 'chemistry') | |
| search | No | Name substring (query_entries) | |
| source | No | Data provenance (add) | |
| target | No | Note target: value name or 'field' | |
| values | No | JSON array of values (compute slide, workspace gcd/lcm/lattice/ratios) | |
| degrees | No | Angle in degrees (trig) | |
| targets | No | JSON targets: {output_name: target_value} (learn, optimize) | |
| to_unit | No | Target unit (unit_convert/unit_factor) | |
| updates | No | Input updates for forward: {input_name: 'new_value'} | |
| function | No | Trig function: sin/cos/tan/all/asin/acos/atan | |
| new_name | No | Name for derived result | |
| sig_figs | No | Significant figures (empty=exact) | |
| store_as | No | Store result in workspace with this name | |
| to_value | No | Target value (route) | |
| wrt_name | No | Differentiate with respect to | |
| dimension | No | Dimension name (list_units) | |
| from_unit | No | Source unit (unit_convert/unit_factor) | |
| intervals | No | Simpson's rule intervals (default: 1000) | |
| max_bound | No | Search bound for solve (default: 1000000) | |
| max_steps | No | Max gradient descent iterations (default: 20) | |
| operation | No | Operation to check (unit_check, domain_check) | |
| read_mode | No | Derive combination: multiply/divide/add/subtract/power/gcd/lcm/sin/cos/tan/log/exp/abs | |
| scenarios | No | What-if scenarios: [{name:str, updates:{input:value}}] | |
| tolerance | No | Convergence tolerance as fraction (e.g. '1/10000') | |
| tool_name | No | Tool name for help manual | |
| from_value | No | Starting value (route) | |
| identifier | No | Alternate query parameter (lookup) | |
| input_name | No | Input variable (solve, sensitivity) | |
| operations | No | Calculation steps: [{values:[str,str], read:'op', label:'name'}]. Reference previous: $prev, $label_name. | |
| search_max | No | Critical points search max (default: 100) | |
| search_min | No | Critical points search min (default: -100) | |
| snapshot_a | No | First snapshot (diff) | |
| snapshot_b | No | Second snapshot (diff) | |
| description | No | Natural language description (recommend) | |
| filter_type | No | Query filter: tag/domain/dimension/similar/precision | |
| output_name | No | Output variable (solve, derivative, gradient) | |
| filter_value | No | Query filter value | |
| output_names | No | JSON array of output names (sensitivity) | |
| target_value | No | Desired output value (solve) | |
| learning_rate | No | Gradient descent step size (default: 1/10) | |
| max_iterations | No | Max iterations for solve (default: 50) | |
| min_similarity | No | Clustering threshold (default: 0.5) | |
| snapshot_action | No | Snapshot op: save/restore/list/delete |
Verify Ownership
This connector has been claimed. The /.well-known/glama.json file has been verified and ownership is confirmed.
Glama periodically re-verifies ownership. If the file is removed, the claim will be revoked.
Control your server's listing on Glama, including description and metadata
Receive usage reports showing how your server is being used
Get monitoring and health status updates for your server
The connector status is unhealthy when Glama is unable to successfully connect to the server. This can happen for several reasons:
The server is experiencing an outage
The URL of the server is wrong
Credentials required to access the server are missing or invalid
If you are the owner of this MCP connector and would like to make modifications to the listing, including providing test credentials for accessing the server, please contact support@glama.ai.
Discussions
No comments yet. Be the first to start the discussion!
Your Connectors
Sign in to create a connector for this server.